Karan's Notes

Daily Routine

Sun, 12 Apr 2026 00:00:00 GMT

The System

No decisions. Follow the clock. Jobs to be done.

Sleep: 11 PM lights out. Phone in another room from 10:30 PM. Wake: 6:30 AM. No snooze. Feet on floor.

Time	Block	What
6:30 AM - 7:00 AM	Wake + Prep	Bathroom, water, gym clothes. No phone.
7:00 AM - 8:00 AM	Gym	Lift. No thinking. Just go.
8:00 AM - 8:30 AM	Shower + Food	Simple breakfast. Still no phone.
8:30 AM - 9:00 AM	Morning Pages	30 min writing. Stream of consciousness. Pen/paper or Obsidian.
9:00 AM - 1:00 PM	Main Quest (Deep Work 1)	4 hours undivided focus. Phone in another room. ONE thing only.

Saturday AM Override

Time	Block	What
6:30 AM - 8:30 AM	Gym + Shower	Same as weekday.
8:30 AM - 9:00 AM	Morning Pages	Same as weekday.
9:00 AM - 12:00 PM	Weekly Review	3 hours. Review what got done. Pick next week’s main quest focus. Prune ideas. Plan, don’t drift.
12:00 PM - 1:00 PM	Publish	Take something from the week’s daily writing, polish it, ship it. Blog post, substack, tweet thread — something goes out every Saturday.

Sunday Override

Time	Block	What
Wake up by 8 AM	No main quest	Sleep in a bit. No deep work.
Morning	Skateboarding	Practice session. Streets, park, wherever.
Rest of day	Free	Cook, explore, adventure list, rest. No guilt.

Time	Block	What
1:00 PM - 2:00 PM	Lunch + Drift + Socials	Eat. TMKOC. Check Twitter/LinkedIn/Reddit. This is your first social media window. Scroll, reply, post — get it out of your system.
2:00 PM - 4:30 PM	Main Quest (Deep Work 2)	2.5 hours. Same rules.
4:30 PM - 5:00 PM	Break	Walk, snack, breathe.
5:00 PM - 6:30 PM	Axe Sharpening	Feeds the main quest but isn’t the main quest. Reading Skiena, Nand2Tetris, Orwell, FPGA research — whatever sharpens the current blade.
6:30 PM - 7:30 PM	Dinner + Family	Chit chat with mom. Khari toast. Protect this.
7:30 PM - 8:30 PM	Tinker Hour	Mon/Wed/Fri = Guitar (30 min timer, sit with it). Tue/Thu/Sat = Hardware (cube, FPGA, physical stuff). Sunday = Free.
8:30 PM - 9:30 PM	Reading	Fiction or essays. Not tech. Orwell, Montaigne, Baldwin, Didion. This expands thinking.
9:30 PM - 10:00 PM	Write	One paragraph minimum. Blog draft, substack post, notes on reading. Doesn’t have to be good.
10:00 PM - 10:30 PM	Socials (Window 2)	Second and last scroll of the day. Post if you have something. Then phone goes to another room.
10:30 PM - 11:00 PM	Wind Down	No screens. Prep for next day — lay out gym clothes, decide tomorrow’s main quest task.
11:00 PM	Sleep

The Rules

No phone before 9 AM. Kills the doomscroll-on-waking loop.
One main quest at a time. Pick ONE project. Minimum 2 weeks before switching.
6.5 hours of deep work is a lot. Protect those hours, waste the rest guilt-free.
Sunday is different. Sleep in till 8. No main quest. Explore, cook, adventure, rest.
Track with a paper checklist. Date + blocks. Check them off. That’s it.
Never miss twice in a row. Skip gym Monday? Fine. Tuesday is non-negotiable. One bad day stays one bad day.
Serendipity through doing, not reaching out. Do the work, post about it online. Let people come to you. The social media windows are for sharing what you built/learned/read — not cold DMs.
Skateboard is commute. Use it to get around during the day. Sunday is for practice.

Tinker Hour Rotation

Day	Activity
Monday	Guitar
Tuesday	Hardware
Wednesday	Guitar
Thursday	Hardware
Friday	Guitar
Saturday	Hardware
Sunday	Free

2025-2026

Sat, 11 Apr 2026 19:52:55 GMT

So this is rough plan, i am not sure whether i will be in bangalore or in ahemdabad or where at that time, but idea is to complete them as much as possible, cause all things i want them to happen!

Every project needs to be somehow contributing to community or other new persons to learn more, fun, and something which i learn a lot and enjoy with good twist, and also idea is to deploy and cary out as many experiments as we can at scale so we can have more information about things, we never know what may work or what not, and what good things can come out of any experiment.

maximising surface area of luck and doing everything in order to achieve it.

projects:

Books:

Skills:

mastering them

rust
python
pytorch
jax
assembly
maths
reverse engineering
skateboarding
video editing
electric guitar
cooking
writing essays and thoughts more on substack(ability to express my thoughts more easily)

goals/metrics:

companies on the radar(grab opportunity if given or create):

Nvidia recommendation engine team(https://developer.nvidia.com/blog/author/eoldridge/)
world models at Meta(Yann LeCun)
Anthropic(Mech Intr)
Deepmind(Mech Intr)

http://neuralnetworksanddeeplearning.com/

Movies:

“Stories We Tell” (2012) directed by Sarah Polley:
- Context: A documentary that investigates the director’s own family secrets. It creates a “meta-narrative” about how different people remember the same event differently, directly paralleling the themes of truth and fabrication in F for Fake.
“Close-Up” (1990) directed by Abbas Kiarostami:
- Context: Based on a true story about a man who impersonated a famous film director. The movie features the actual people involved re-enacting the events. It is a masterpiece of deconstructing the “truth” of cinema.
“The Gleaners and I” (2000) directed by Agnès Varda:
- Context: Varda is the godmother of the cinematic essay. This film is a wandering, personal exploration of “gleaning” (collecting leftovers), but it is structured by her own curiosity rather than a traditional plot, much like a video essay.
“Exit Through the Gift Shop” (2010) directed by Banksy:
- Context: Startlingly similar to F for Fake. It starts as a documentary about street art but evolves into a question of who is conning who. It questions the value of art and the “expert” opinion.

Adventure & Explore

Take a train to a random city and figure it out when you get there
Sleep under the stars somewhere you’ve never been
Visit a town with a population under 500
Eat alone at a fancy restaurant and enjoy every second of it
Get on a flight with only a carry on and no hotel booked
Find the highest point in your city and watch the sunset from there
Walk into a museum you’ve never noticed before
Spend a full day in a neighborhood you always drive past

Strike up a real conversation with a stranger at a café and actually listen
Write a letter to someone who changed your life and actually send it
Attend an event where you know absolutely no one
Compliment five strangers in one day and mean every word
Call an old friend you haven’t spoken to in years with no agenda
Cook a full meal for someone who needs it right now
Ask an elderly person about their biggest regret and listen without your phone

functional programming

Sat, 11 Apr 2026 19:52:55 GMT

https://people.csail.mit.edu/rachit/post/why-study-programming-languages/

https://steshaw.org/plt/

https://cs.lmu.edu/~ray/notes/languagetheory/

https://mpc.sh/blog/a-gentle-intro-to-plt

https://en.wikibooks.org/wiki/Introduction_to_Programming_Languages

hardcaml FPGA

Sat, 11 Apr 2026 19:52:55 GMT

hardcaml hardcaml custom open source FPGA SSD with hardcaml FPGA book on hitchikers guide to FPGA

all this things: https://intel.github.io/rohd-website/

open source FPGA silicon : https://github.com/MidstallSoftware/aegis

https://anil.recoil.org/notes/fpgas-hardcaml https://anil.recoil.org/ideas/tracing-hdl-with-effects https://anil.recoil.org/ideas/computational-storage-for-vector-dbs

claude conversation:

what will we achive which hardcaml can’t do with this thing or in genreal comparsion with other hdl in the ecoyssytem from dart to haskell clash

https://anil.recoil.org/ideas/tracing-hdl-with-effects

Great read — this is a research proposal by Anil Madhavapeddy (Cambridge) for an MPhil project exploring OCaml 5 effects as a foundation for a tracing-style HDL. Let me break down exactly what this achieves vs. HardCaml, and how it positions in the broader ecosystem.

The Core Idea: Tracing vs. Building

The fundamental distinction is how the circuit graph gets constructed.

HardCaml today — combinator / data-structure style: You write OCaml that builds up a circuit as a data structure. Your OCaml program’s output is the circuit. This requires heavy use of the OCaml module system (functors, first-class modules, typed interfaces) to compose components. It’s powerful but has a steep learning curve — you’re always mentally managing two layers: the OCaml meta-level and the hardware object-level.

The effects-based tracing HDL — direct execution style: You write OCaml that directly looks like the circuit it describes. You evaluate OCaml code, and the effect handlers intercept and record what happened — building the circuit graph as a side effect of running the program. The circuit emerges from tracing execution, not from explicitly constructing a data structure.

What This Buys Over HardCaml Specifically

1. Ergonomics & accessibility HardCaml’s module-system-heavy approach is a productivity wall. It makes very heavy use of the module system to build up the circuit description as an OCaml data structure recoil, which means you need to be fluent in OCaml’s more advanced features (functors, module signatures, first-class modules) before you can be productive. The effects approach lets you write code that reads like ordinary imperative/functional computation — the tracing machinery is transparent.

2. Control-flow memoization via effects This is the deeper technical win. Effect handlers can intercept recursive calls and memoize their circuit-graph expansions, which means shared subgraphs don’t get duplicated. In a plain combinator HDL you have to manually thread sharing; here the handler does it structurally.

3. Restricting recursion properly Arbitrary recursion in hardware is a problem (it implies infinite logic). Effects let you intercept recursive calls and decide how to handle them — either unrolling a fixed number of times, requiring explicit register boundaries, or rejecting unbounded recursion statically. This is a semantic guarantee you can enforce via the handler rather than relying on programmer discipline.

4. Fixed-length vectors ergonomically Hardware is full of [N]bit types. HardCaml encodes these but it’s verbose. The proposal explicitly targets this as an ergonomics win to explore.

Comparison Across the Ecosystem

HDL	Host language	Style	Key strength	Key weakness
Verilog / VHDL	Domain-specific	Structural/RTL	Industry standard, tool support	Weak abstraction, verbose, no types
HardCaml	OCaml	Combinator / data-structure	Strong typing, Jane Street production use, module polymorphism	Module-system learning cliff, two-layer mental model
Clash	Haskell	Tracing (type-directed)	Looks like Haskell functions, REPL, fixed-length Vec types, type inference	GHC type-level complexity, long compile times, Haskell ecosystem barrier
Chisel	Scala	Embedded DSL / combinator	JVM ecosystem, industry adoption, good tooling	Scala complexity, Spark-style boilerplate, runtime errors
SpinalHDL	Scala	Combinator	Cleaner than Chisel, good abstractions	Niche, small community
Amaranth (nMigen)	Python	Combinator	Accessible, fast iteration, Python ecosystem	Dynamic typing catches errors late, Python perf for large designs
Lava / Kansas Lava	Haskell	Combinator (arrows)	Theoretically clean	Effectively abandoned
This proposal (OCaml effects HDL)	OCaml 5	Tracing via effects	See below	Research prototype — not production

The Clash Comparison Is Central

Clash uses a number of advanced Haskell type-level features to encode fixed-length vectors and has an interactive REPL that allows for exploration without requiring a separate test bench. recoil

Clash is the closest spiritual ancestor. It achieves the “write hardware like functions” feel through Haskell’s lazy evaluation + GHC’s rewriting + type-level naturals for Vec n a. The tracing HDL proposal wants to achieve the same feel in OCaml, but through a structurally different mechanism:

Clash traces by exploiting Haskell’s lazy graph reduction — the program graph is the circuit graph, extracted by GHC’s normalizer. You’re fighting GHC internals.
Effects HDL traces by using explicit delimited continuations (effect handlers) to intercept evaluation. This is semantically cleaner, more inspectable, and doesn’t depend on compiler internals.

The OCaml approach could be more predictable than Clash because you don’t rely on GHC’s optimizer doing the right thing — the tracing boundary is explicitly defined by the effect handler.

The Dart Angle

There’s no serious Dart HDL in the ecosystem. The closest thing would be using Dart for FPGA scripting/tooling (e.g. ROHD from Intel uses Dart as the host), which is more in the Amaranth territory — accessible dynamic language, combinator style. It gains Python-like ergonomics but loses the type-level guarantees that make Clash/HardCaml interesting. The effects proposal is at the opposite end: it wants more semantic power and correctness guarantees, not less.

What Would Genuinely Be Novel

If the effects approach works, the real contribution is:

A new point in the design space: tracing-style HDL that doesn’t require a lazy language or compiler internals to work, but instead uses first-class algebraic effects as the mechanism.
Effect handlers as a hardware/software duality tool: the same OCaml code could be run natively for simulation (handler = execute normally), or traced for synthesis (handler = build circuit graph), or partially evaluated (handler = mixed). One program, multiple interpretations — this is the “finally tagless” / multi-stage dream done cleanly.
Recursion control as a first-class citizen, not a linting afterthought.

The open question is whether OCaml 5 effects are expressive enough to handle the multi-shot continuation patterns needed for circuit sharing and unrolling. The memo.ml example in the effects-examples repo suggests yes, but at scale in hardware design it remains to be proven.

what would be good project to implment in this hdl to get idea about how good ocaml5 effects are there, like open source fpga or some other thing or suggest something good

This is a great question. You want something that stresses the effect system in interesting ways — not just “does it work” but “where does it shine or crack.” Let me think through this carefully.

What Makes a Good Test Case

You want a project that exercises:

Structural sharing — same subgraph reused many times (tests memoization via effects)
Controlled recursion — natural recursion that must be unrolled to fixed depth
Fixed-length vector arithmetic — the ergonomics win over HardCaml
Multiple interpretations — same code simulated, synthesized, and maybe formally verified

Tier 1: Best Bang for Effort

A Systolic Array for Matrix Multiply

This is the perfect first serious project. A systolic array is a grid of identical processing elements (PEs) where data flows rhythmically between neighbors.

Why it’s ideal:

The PE is defined once, instantiated N×M times — directly tests whether effect-based sharing deduplicates the graph properly or explodes it
The grid wiring is naturally expressed as a recursive function over indices — tests controlled recursion unrolling
It’s the exact architecture inside TPUs, and is a hot target for open-source FPGA ML accelerators (like FINN)
Small enough to complete, deep enough to be real

What you’d learn about OCaml effects: whether memoization via effects correctly identifies structurally identical PE instances, and whether the tracing produces a flat efficient netlist rather than N×M duplicate subgraphs.

A Pipelined RISC-V Core (RV32I)

Not a full core — just the 5-stage pipeline: Fetch → Decode → Execute → Memory → Writeback.

Why it’s ideal:

Pipeline hazard logic is naturally expressed as conditional forwarding — great test of how control flow in the host OCaml maps to mux logic in the traced circuit
Register file is a fixed-length vector of 32 registers — directly tests the Vec ergonomics
There are excellent open-source reference implementations (PicoRV32, VexRiscv, SERV) to validate against
The RISC-V spec is clean and minimal — you spend time on the HDL problem, not architecture archaeology

What you’d learn: how well recursive/structured decode logic traces, and whether the effect handler correctly handles the stateful pipeline registers vs. combinational logic distinction.

Tier 2: Sharper Tests of Specific Effect Properties

A Parametric FIR Filter Bank

A bank of N FIR filters sharing tap coefficients.

Why interesting: this is the canonical test for structural sharing. In a naive combinator HDL you’d get N×M multipliers. With correct memoization effects, shared constant-coefficient multipliers should collapse. This is a very targeted stress test of the memo effect specifically — you’d know within 200 lines whether the approach works or has fundamental issues.

A SHA-256 / AES-128 Core

Cryptographic cores are beloved FPGA targets and have:

Highly regular round structures (natural recursion to unroll)
Fixed 32/64-bit word widths everywhere (Vec ergonomics)
Well-known reference outputs for testing

The round function is defined once and applied N times — a direct test of whether for-style unrolling via effects produces correct pipelined or iterative hardware. There’s also an open-source reference in every HDL imaginable to compare netlists against.

A UART / SPI Controller

Deceptively good for testing the simulation vs. synthesis duality. A UART is a simple state machine, but:

You want to run it in OCaml natively with a mock byte stream (simulation handler)
Then trace it to Verilog (synthesis handler)
Then maybe hook it to a formal tool to verify the baud rate arithmetic (verification handler)

Same OCaml code, three handlers, three interpretations. This is the cleanest possible demo of the effects-as-multiple-backends idea and fits in ~500 lines.

Tier 3: Ambitious / Research-Grade

A Sparse Attention Accelerator

Given the FPGA+vector-DB usecase Anil mentions on the same site, implementing a hardware block for sparse dot-product attention would be genuinely novel. The challenge: irregular sparsity patterns mean the circuit structure itself becomes data-dependent — a hard case for any tracing HDL.

Connecting to OpenROAD / Yosys

Rather than targeting Verilog output → vendor tools, you could target the RTLIL (internal format of Yosys, the open-source synthesis tool) directly from your effect-traced AST. This would make the whole flow open: OCaml effects → RTLIL → OpenROAD → GDS. No proprietary tools anywhere.

Concrete Recommendation

Start with the FIR filter bank (2–3 days, laser-focused on the memo effect), then graduate to the systolic array (the real project). These two together will tell you definitively whether OCaml 5 effects are genuinely better than Clash’s lazy-graph approach or HardCaml’s explicit modules — specifically on the sharing and recursion problems that matter most in real synthesis.

The UART is the right companion project to validate the multi-handler / multi-interpretation story, which is arguably the most novel claim in the whole proposal.

kids metal songs

Sat, 11 Apr 2026 19:52:55 GMT

this is good genre music, and vibe is also good, i really liked it, i think this and cool beats and music and rap would be killer combo

self balancing music player

Sat, 11 Apr 2026 19:52:55 GMT

I want to make my own music player which self balances itself with cool rgb cube and projection and when i move in certain things it should interactively change the music and other things maybe a projector or something with alexa kind of system which is built in itself.

https://willempennings.nl/balancing-cube/ https://github.com/willem-pennings/balancing-cube/ https://oshwhub.com/nokia82/cubli_-ping-heng-li-fang-ti

this guy has really great UI and display ideas: https://x.com/adamfuhrer https://www.instagram.com/adamfuhrerart and mohenjo daro style art would do just fucking great

bare metal shaders would just do crazy thing

https://www.olwal.com/ has good idea about HCI

https://www.reddit.com/r/IndustrialDesign/comments/1sfo2fl/snapshots_inner_workings_of_my_cube_lamp_design/?utm_source=share&utm_medium=web3x&utm_name=web3xcss&utm_term=1&utm_content=share_button

attach cool display to show current playing music song:

https://github.com/remrc/Self-Balancing-Cube

base plate is wireless charging thing, just drop it and it would charge

stoned monk engineering

Tier	Material	Machining Difficulty	Margin
Standard	Aluminum	Easy	Best
Stealth	Anodized black aluminum	Easy	Best
Heritage	Brass	Medium	Great
Aerospace	Titanium	Hard but predictable	Good
Obsidian	Zirconium (heat-blackened)	Hard but predictable	Good

GC-Fuzz

Wed, 08 Apr 2026 18:39:54 GMT

https://dl.acm.org/doi/epdf/10.1145/3733598 https://github.com/BurryPotter/GCFuzz https://github.com/JikesRVM/JikesRVM

read this shit first: https://bushido-sec.com/index.php/2025/01/03/fuzzing-harness-guide/

paper: https://rmod-files.lille.inria.fr/Team/Texts/Papers/Poli23a-ICST-HeapFuzzing.pdf

start with fuzzing mmtk: https://github.com/mmtk/mmtk-core

old harness: https://github.com/JikesRVM/JikesRVM/tree/master/MMTk/harness

https://github.com/rust-fuzz

https://rust-fuzz.github.io/book/introduction.html

https://www.steveblackburn.org/research/projects/gc-fuzzing/

once harness is done unleash the llms: https://arxiv.org/html/2512.03420v2

things i have gone throug:

https://tutorial.ponylang.io/gotchas/garbage-collection.html#garbage-collection-in-pony https://tutorial.ponylang.io/runtime-basics/garbage-collection#actor-collection-inter-actor-gc-via-orca https://www.mono-project.com/docs/advanced/garbage-collector/sgen/working-with-sgen/ https://www.mono-project.com/docs/advanced/garbage-collector/sgen/

https://www.youtube.com/live/lGM37Z3oDKw?t=12105s

Rex-Minecraft Robo Dog

Wed, 08 Apr 2026 18:39:54 GMT

Rex is my Minecraft dog, so i am bringing to this real life

https://www.reddit.com/r/robotics/comments/1rqvaeu/deep_robotics_has_built_a_robot_horse_seemingly_a/

make it unicorn whih can fly also

link: https://www.instagram.com/p/DMdc7UyIyDc/?utm_source=ig_web_copy_link

Component	Quantity	Price per Unit (INR)	Total (INR)
Servos (LX-16A)	12	750	9,000
Jetson Orin Nano	1	45,000	45,000
Battery (2S LiPo)	1	1,500	1,500
Sensors (Camera + IMU)	1 + 1	1,000 + 100	1,100
Audio Devices (Mic + Speaker)	1 + 1	500 + 500	1,000
Power Management (Regulator)	1	200	200
3D Printing (Chassis)	1	5,000	5,000
Total			63,800

Component Category	Item	Estimated Unit Cost (USD)	Quantity	Estimated Total Cost (USD)	Estimated Total Cost (INR)	Notes
Main Processing Unit	NVIDIA Jetson Orin Nano Super Developer Kit	$249.00	1	$249.00	₹21,508.62	Chosen for its AI performance and ecosystem.
Actuators (Servos)	High-Torque Digital Serial Bus Servo (e.g., Hiwonder HX-35H)	$25.00 (average)	14	$350.00	₹30,233.00	12 for legs (3 per leg), 2 for head/tail.
Servo Control	ROS Robot Control Board with STM32	$100.00 (estimate)	1	$100.00	₹8,638.00	For managing multiple servos and ROS integration.
Power Management	High-Capacity LiPo Battery Pack (e.g., 12V 3000mAh)	$40.00 (estimate)	1	$40.00	₹3,455.20	For robot’s operational autonomy.
	DC-DC Buck Converter	$8.00 (estimate)	1	$8.00	₹691.04	To provide stable voltage to different components.
Sensors	High-Definition Camera Module (e.g., RPi V2/V3 compatible)	$30.00 (estimate)	1	$30.00	₹2,591.40	For AI vision tasks like object recognition.
	IMU Sensor (9-axis)	$45.00	1	$45.00	₹3,887.10	For balance, orientation, and stability.
	USB Audio Codec Module with Microphone	$72.00 (estimate)	1	$72.00	₹6,219.36	For natural language input to the LLM.
	Small Speaker Module	$5.00 (estimate)	1	$5.00	₹431.90	For audio output and robot responses.
Fabrication Materials	3D Printing Filament (PETG/ABS, ~3kg)	$25.00 (per kg estimate)	3	$75.00	₹6,478.50	For chassis and limb components.
Miscellaneous	Screws, nuts, wires, connectors, tools, etc.	$150.00 (estimate)	1	$150.00	₹12,957.00	Essential small parts and assembly tools.
Total Estimated Cost	---	---	---	$1,184.00	₹102,653.12	Please note: These are estimates. Prices can vary due to vendors, specific models, and import duties/taxes in India.

https://docs.kscale.dev/docs/ksim#tutorial

https://www.youtube.com/watch?v=c64FnSvj8kQ&t=166s

idea is to create cheap(<$1000) DIY minecraft style robot kit which just works and easy to setup, and moduler enough so people can do whatever they want to do!

need good amount of money for this, and need more foundation, need to apply to all fellowships

make it do skate and make it also fly fucking fly!

https://www.youtube.com/watch?v=S4eQXXxUnNE

writing

Wed, 08 Apr 2026 18:39:54 GMT

Ancient / Classical

Marcus Aurelius — Meditations (180 AD)
Seneca — Letters from a Stoic

Renaissance / Early Modern

Montaigne — Essays (1580) — literally invented the essay form
Francis Bacon — Essays (1597)

18th Century

Benjamin Franklin — Autobiography (1791)
Samuel Johnson — The Rambler essays

19th Century

Ralph Waldo Emerson — Self-Reliance (1841)
Henry David Thoreau — Walden (1854)

20th Century

George Orwell — Politics and the English Language (1946) — read this first, before anything else
E.B. White — Once More to the Lake (1941)
James Baldwin — Notes of a Native Son (1955)
Joan Didion — Slouching Towards Bethlehem (1968)
David Foster Wallace — Consider the Lobster (2004)

Contemporary

Paul Graham — essays 2000s–present
Christopher Hitchens — Arguably (2011)

George Orwell Read Politics and the English Language first

https://mathshistory.st-andrews.ac.uk/Extras/Keynes_Newton/

This Is Water David Foster Wallace Commencement Speech https://www.youtube.com/watch?v=DCbGM4mqEVw

Christopher Hitchens His essays collected in Arguably. Teaches confidence of voice — he never hedges when he doesn’t need to. Good antidote if your writing tends to be timid.

James Baldwin Notes of a Native Son and The Fire Next Time

Michel de Montaigne https://hyperessays.net/essays/toc/

8th April 26

Wed, 08 Apr 2026 18:39:54 GMT

It’s been like hazy morning, waking up then actually waking up after 1 hr, taking a dump with information overloading my brain, i think this is what normal day from last few weeks is looking like, consuming lot of social media and news tech, articles, blog and after sudden crash drifting in the time slowly, just thinking about what can be done or this is good idea etc.., till this happens it is around 12, then i am little hungry, then i usually find my self crawling to the food and having it while watching tmkoc, then slowly drifting away in the sleeping position while feeling i am doing some productive while the whole thing is just bs and productivity porn kind of thing, i fell to sleep, while i am sleeping or which feels like i am sleeping my mind is quite active and it’s been screaming that i should do this i should do that this is the time etc.., i every day think about going to gym in the morning and in the evening but i don’t go cause in the morning i am mostly sleeping and in the evening i am doomscrolling or doing some random shit which i don’t know feels very important in that present moment but it is always useless thing, if i would have skipped it, it wouldn’t have any single impact or change, but still i end up doing it, after i wake up i usually i goto main hall do chit chat and brain picking of my mom and enjoy khari toast and just simply drift away in the time more, then i either go to garden for a walk for 1 hr or just simply find some other intellectual curiosity think and just drift away in that, i complete my dinner same daily food ritual and doing chitchat with my mom, then i go to my room, in the whole day if i got some motivation then i play guitar A and D chord to just practice but not for more than 5min, cause those 5min feels like total 1 hr, after dinner i then again start koala ritual again drifting away either slowly in the nap or again some random rabbit hole without doing any thing and thinking we will do something tomorrow, and i mostly go to sleep around 1 or 2 AM, and the day starts again like this on the next days, same thing no difference, just few here and there minor changes.

This is what is happening from almost daily after i left the Krupal and the project i think around 2-3 weeks, in initial weeks i had projects and ideas and deadlines so i was working towards them, i really work great when i have some kind of realistic deadline ahead of me and because i don’t have deadline or some hanging sword above me last week has been just drifting the time and just feeding my mind with all kinds of information which feels like i am doing something important or making some progress but where and which direction no one knows. I have been fantasising the whole Chennai thing and piggybacking on that, which i feel is wrong thing but my whole mind is not able to stop thinking about it, the deadline for that thing is around 20th April, i almost submitted my application 1 month ago to the deadline, I know they are going to grill my really hard on the interview cause if i were them then i would have also done the same thing, cause on paper many people look really great but in real they are many times are not, and in the age of LLM it is going to get more worse then worse, so i am expecting getting really grilled by them, and that’s why the whole last 1.5 week i have been thinking about getting my self ready and prepared for the thing, but i am just drifting away from the thing i think main reason is somewhere my inner self thinks that as deadline and things move in the fast pace momentum i will wake up and lock in, but i know those last moment things one always try to sneak in and find the hacks and rushes the whole thing, but i don’t want to do that this time, cause this whole thing can really change the whole thing and future for me, and where the things are going i think that is the best opportunity for piggy backing and building great intuition and discipline.

So start doing small things and complete them like jobs to be done and forget about other things no overthinking just it is jobs to be done!

Co2 Remove

Tue, 07 Apr 2026 14:27:56 GMT

Ocean-Based Carbon Removal is genuinely underexplored and potentially massive margin territory. Two variants:

Seaweed farming at scale — grow kelp, it absorbs CO₂, sink it to deep ocean. Permanently removed. Cost potentially very low given India’s coastline. But methodology approval is still nascent — registries haven’t fully figured out how to verify it yet. Early mover advantage is enormous here.

Ocean Alkalinity Enhancement (OAE) — essentially ERW but done in seawater instead of farmland. Crush limestone or similar minerals, dissolve in ocean, accelerates natural carbon absorption. Some people think this is the largest scale carbon removal pathway that exists — oceans can absorb vastly more than land. Still very early stage scientifically but a few startups globally are working on it.

Soil Carbon Sequestration via Regenerative Agriculture — this is what Varaha mainly does alongside biochar. Lower margin ($15-50/tonne) but the volume potential is staggering given India’s farm coverage. Margin per credit is thin but if you’re doing 10 million tonnes a year the absolute numbers work.

Peatland and Wetland Restoration — one of the most carbon-dense ecosystems on the planet. Degraded peatlands release enormous CO₂. Restoring them locks it back. India has some peatland, Southeast Asia has massive reserves. Credits sell at $50-150/tonne and the science is well established. Very underpursued in India.

Mineralization via Industrial Waste — some industrial processes produce alkaline waste (steel slag, cement kiln dust, fly ash) that naturally absorbs CO₂ when exposed to air. You’re essentially getting paid to dispose of industrial waste and generating carbon credits from the same transaction. Margin structure is very interesting — negative feedstock cost essentially.

sabbatical stuff

Tue, 07 Apr 2026 14:27:56 GMT

thinking for going on the learning sabbatical vacation!

things which i am learning and completing:

Core:

Nand2Tetris
SICP
⁠⁠math book jeremy kun (https://agorism.dev/book/math/intro/Dr.%20Jeremy%20Kun%20-%20A%20Programmer%E2%80%99s%20Introduction%20to%20Mathematics-CreateSpace%20Independent%20Publishing%20Platform%20%282018%29.pdf)
An Infinitely Large Napkin (https://web.evanchen.cc/napkin.html)
Game engine architecture by jason gregory

Scaling:

Performance Engineering: https://www.youtube.com/playlist?app=desktop&list=PLUl4u3cNGP63VIBQVWguXxZZi0566y7Wf
distributed systems: https://www.youtube.com/playlist?list=PL4YhK0pT0ZhXTRSAYHAgBcJkhlM2hlhw3
competitive programing
long form essays writing
creating content in all forms(text, images, videos, reels, short, yt vlog everything)

AI:

JAX
https://jax-ml.github.io/scaling-book/
world models
RL
fast ai deep learning course

Robotics:

Music:

electric guitar
carnatic music

photography:

traveling and clicking some photos with good camera

https://github.com/skyzh/mini-lsm https://github.com/skyzh/write-you-a-vector-db

https://dlsyscourse.org

https://www.cs.cmu.edu/~mgormley/courses/10601/

https://spinningup.openai.com/en/latest/

Game Studio

Tue, 31 Mar 2026 06:11:28 GMT

I think we can build really great very lean game studio and produce really hit games!

cachehit

https://github.com/MaximumADHD https://github.com/pizzaboxer

https://rojo.space/

Journey to the cool

Tue, 31 Mar 2026 06:11:28 GMT

Trazillion dollar idea.

Make a game engine, a decent one, that supports basic stuff, but that could be heavily extended and modified. But make it unconventionally console / test driven, make it easily verifiable. Then, make a lot of toy game with it. Get lot of instructions, Train (fine-tune) an LLM on it. Sell the LLM & game engine as a paired product. Train on the user-generated games. SFT. RLVR.

https://entropygames.ai/research/building-the-next-generation-of-games?v2&curius=1819

ecommerce-os

Tue, 31 Mar 2026 06:11:28 GMT

I kind of want to build an OS which is perfect to run ecommerce buisness on from website to managing multiple platfrom shopify to amazon to quick commerce, to marketing to gtm, to ads targeting on linkedin, facebook instagram etc.. to inventory and dispute management, all things in one place and with AI workflows which boosts productivity in great way,customers review to customer support all gets fuled back in one system, where the os connects to everything and if you are not using it then it provides default options also, the system tells where you are loosing most of your margins, how is your buisness going what is the main bottlneck in your buisness, the modality is changing owner don’t want to replace existing systems, cause need to educate people retrain them etc.. but what he can do is gather things at one place which gives him great inteligence layer.

good photos on models, videos etc… full bundle scheme

Crazy level Vertical Integration!!!

also include the intra search like that chinese search site and integrate it in our platform but don’t expose it, https://en.52wmb.com/

either need to quire clicktech retail or get the data somehow

where the goods imported(ships export data) goods being sold or processed(clicktech and amazon sales data or category keyword data from individual buyer stuff) manufacturing data(who makes it how much raw material, who process it how much, where it goes what does it get etc…, something like ofbuisness or something needs to be capture where the data keeps getting flown to us and the stuff keeps running itself)

need to somehow tap into croma and reliance retail for more specific geographical offline data to enter in offline retail and dmart and other supply chain for fmcg industry

also need to think about some customer motivated data entry or some mechanism so we get more granuler data which customer willingly shares

and if we can’t get to the retailer specific detail, get the retailer, distributors and poach them

pilars:

Data/Intelligence
Marketing/Sales/GTM(better Ads manager, influencer marketing to other all kinds of marketing which is out there)
After Sales(reviews, brand perception from customer side etc…)

and absorbing all the clay and attio tools inside one thing, and ultimate thing is building simulation software based on agents to predict consumer behaviour and AI(https://arxiv.org/pdf/2304.03442)(https://arxiv.org/pdf/2603.05923)(https://arxiv.org/pdf/2502.08691)

combine this with news and other market events to predict and help with opportunity and prediction with price and future events(oracle kind of thing)

Phase 1 (M0–5) → Don’t build the OS. Build the wedge. One brutal margin intelligence tool. Get 15–30 paying brands. Build the data asset.

Phase 2 (M5–10) → Expand integrations, add inventory + ads + support hub. First automation agents. Now you’re sticky.

Phase 3 (M10–16) → Full agent layer. Dispute automation, supplier agent, ad optimisation agent, support agent. This is where you replace 2–3 headcounts per customer. Pricing jumps.

Phase 4 (M16–24) → Platform play. API, white-label for agencies, app marketplace. Distribution becomes self-compounding. You stop selling — the ecosystem sells for you.

The key discipline: resist Phase 2 features while in Phase 1. The wedge only works if it’s sharp.

Affiliate marketing to influencer management to all things

https://www.tryglimpse.com/

gc-rust

Tue, 31 Mar 2026 06:11:28 GMT

https://manishearth.github.io/blog/2015/09/01/designing-a-gc-in-rust/ https://github.com/Manishearth/rust-gc/

lxr: https://arxiv.org/pdf/2210.17175

other implementation:

https://github.com/fitzgen/bacon-rajan-cc

https://github.com/asajeffrey/josephine/

https://github.com/withoutboats/shifgrethor

https://gist.github.com/Manishearth/70856e2f01e18935681c

they forked the thing:

https://soft-dev.org/pubs/html/hughes_tratt__garbage_collection_for_rust_the_finalizer_frontier/

GC-fuzz: Build it as a testing harness crate, not as a GC crate. That keeps scope sane and makes the “Antithesis in spirit” part explicit: perturb, assert, replay, shrink.

Shape Call it something like gc-fuzz, gc-schedule, or gc-check.

Split it into four pieces:

event Defines the observable moments in a collector or mutator:

pub enum GcEvent { Alloc { bytes: usize, object_id: u64 }, RootAdded { root_id: u64 }, RootRemoved { root_id: u64 }, WriteBarrier { from: u64, to: u64 }, Safepoint, CollectionStart, CollectionEnd, }
schedule Decides what perturbation to apply:

pub enum Decision { Noop, CollectNow, VerifyHeap, PoisonFreed, }

pub trait Schedule { fn on_event(&mut self, event: &GcEvent) → Decision; }
recorder Logs decisions so failures are reproducible:

pub struct TraceStep { pub event_index: u64, pub event: GcEvent, pub decision: Decision, }

pub trait Recorder { fn record(&mut self, step: &TraceStep); }

oracle Verifies invariants:

pub trait HeapOracle { type Error;

fn verify_pre_gc(&self) -> Result<(), Self::Error>;
fn verify_post_gc(&self) -> Result<(), Self::Error>;

}

Minimal API Your collector integrates at safepoints:

pub trait HarnessHost { type Error;

  fn collect_now(&mut self) -> Result<(), Self::Error>;
  fn verify_heap(&mut self) -> Result<(), Self::Error>;
  fn poison_freed(&mut self) -> Result<(), Self::Error>;

}

Then the harness itself is just:

pub struct Harness<S, R> { schedule: S, recorder: R, event_index: u64, }

impl<S: Schedule, R: Recorder> Harness<S, R> { pub fn on_event<H: HarnessHost>( &mut self, host: &mut H, event: GcEvent, ) → Result<(), H::Error> { let decision = self.schedule.on_event(&event); self.recorder.record(&TraceStep { event_index: self.event_index, event, decision, }); self.event_index += 1;

      match decision {
          Decision::Noop => Ok(()),
          Decision::CollectNow => host.collect_now(),
          Decision::VerifyHeap => host.verify_heap(),
          Decision::PoisonFreed => host.poison_freed(),
      }
  }

}

That is the right abstraction boundary. The harness decides when to perturb. The GC still owns how collection works.

First three scheduler modes These are enough for v1:

Stress Trigger CollectNow on every alloc and safepoint.
Seeded Deterministic PRNG, decisions derived from seed plus event count.
Replay Read a previously recorded TraceStep sequence and emit exactly the same decisions.

Do not start with “adaptive”. That is a production policy problem, not a testing tool problem.

The feature that actually matters Add a trace shrinker. Given a failing replay trace, minimize it.

Representation:

pub struct DecisionTrace(pub Vec);

pub struct DecisionPoint { pub event_index: u64, pub decision: Decision, }

Shrinking strategy:

Remove half the decision points, replay.
If still fails, keep the smaller half.
If not, restore and try smaller chunks.
Once coarse minimization finishes, try dropping single points.
Report the minimal failing schedule.

This is just delta debugging, boring in the good way. That is the part that feels most “Antithesis”.

What properties to check For a non-moving mark/sweep collector, start with these:

Every root points to a live object after collection.
Every reachable object remains allocated after collection.
No edge points to freed memory.
Running GC twice with no mutation yields the same live set.
Freed objects are not reachable from any root.
Finalizers run at most once.

For a moving collector, add later:

Every forwarded pointer resolves to a valid to-space object.
No stale from-space pointer survives in roots or fields.
Barrier invariants hold before and after each phase.

How to test the harness Do not mock the world into nonsense. Build a tiny real heap model:

object arena as Vec
object fields as Vec
real root set
simple mark/sweep implementation
intentionally buggy variants behind test cfg

Then write end-to-end tests:

stress_finds_missing_root_bug Simulate a root registration bug that only fails if collection lands between alloc and root_add.
seed_reproduces_failure Save failing seed, rerun, assert same failure.
replay_reproduces_failure Record a trace, replay it, assert identical failure.
shrink_reduces_trace Start from a long failing trace, shrink it, assert the smaller one still fails.

That gives you real proof, not brochureware.

Two-week plan Week 1:

Implement GcEvent, Decision, Schedule, Recorder, HarnessHost.
Add Stress, Seeded, and in-memory Recorder.
Build the tiny reference mark/sweep heap.
Write one intentionally buggy scenario and make Stress catch it.

Week 2:

Add Replay.
Add trace serialization with serde if you want CLI ergonomics.
Implement delta-debug style shrinking.
Write one post: “A failing GC schedule, recorded and minimized”.

What not to do

Do not start with concurrent GC.
Do not start with a brand new algorithm.
Do not start by integrating five runtimes.
Do not oversell “determinism” if allocator layout and threads are still nondeterministic.

Best framing Pitch it like this:

“A property-driven GC testing harness for Rust collectors. It forces collections at hostile times, records the schedule, replays failures exactly, and shrinks failing schedules to minimal repros.”

Incremental Sheet Forming

Sun, 01 Mar 2026 17:29:59 GMT

https://en.wikipedia.org/wiki/Mishra_Dhatu_Nigam https://bhukhanvala.in/

Market Validation Questions

For Defense:

Who is the actual procurement officer at DRDO/HAL for sheet metal components?
What is their current vendor list and approval process?
How long does vendor qualification take? (Could be 2-5 years)
What specific programs have upcoming prototype needs?
What materials are they working with? (AL 7075? Ti-6Al-4V? Inconel?)
What’s their budget cycle? When do they release RFPs?
Is there a Make in India mandate that helps you?

For Space:

Which private space startups have raised enough money to actually buy?
What’s Skyroot/Agnikul spending on metal forming currently?
Does ISRO have a vendor development program you can join?
What certifications do you need? (AS9100? NADCAP?)

For Architecture:

Can you get 3-5 architects to sign LOIs (Letters of Intent)?
What’s the typical project budget for facade work?
Who makes the vendor decision — architect or contractor?
What’s the lead time expectation? (ISF might be too slow for construction schedules)

Technical Validation Questions

What’s the thickest material you MUST form? (1mm? 3mm? 6mm?)
What’s the largest part dimension you MUST hit? (Is 12ft actually necessary?)
What materials are non-negotiable? (If titanium is required, that changes everything)
What surface finish is acceptable? (Ra 3.2µm? Ra 1.6µm? Class A?)
What dimensional tolerance is required? (±1mm? ±0.5mm? ±0.1mm?)
Do you need to form both sides (convex AND concave features)?

Unit Economics Questions

What do customers currently pay for equivalent parts?
- Hand-beaten panel: ₹____/sq ft
- Imported formed part: ₹____/kg
- Machined from billet: ₹____/kg
What’s your target price point to be competitive?
How many hours will a typical part take to form?
At ₹X/hour machine rate, does the math work?
What’s the capital cost you can afford?
- ₹25 lakh? ₹50 lakh? ₹1 crore? ₹5 crore?
What’s your break-even volume?

Competition Questions

Who else in India is doing ANY kind of advanced forming?
Is anyone importing AMINO or MECO machines?
What are IITs doing with their ISF research? Any spin-offs?
Could IIT Bombay/Madras/Hyderabad be a partner or competitor?

Go-to-Market Questions

Should you start as a job shop (you make parts) or machine seller (you sell machines)?
Should you offer “Forming as a Service” first to validate demand?
Can you partner with an existing sheet metal fabricator who has customers?
Should you locate near a defense cluster (Bangalore, Hyderabad, Pune)?

parts up to 12 ft (3.7 m) long and 5 ft (1.5 m) deep, and can shape structural sheet up to 1/4” (6.35 mm) thick with sub-millimeter precision.

Aluminum Alloys (2xxx, 5xxx, 6xxx, 7xxx )
Mild Steels (A1011)
Stainless Steels* (304, 304L, 316, 316L)
Nickel-Based Superalloys* (625, 718)
Low Expansion Alloys* (Invar 36)
Refractory Alloys* (Niobium C103, Haynes® 230)
Other Specialty Alloys* (HyMu 80®, Magnesium, Brass, Bronze)

hire this people: https://www.linkedin.com/in/miguel-angel-zamora-mora-b97030107/?originalSubdomain=ch

https://scholar.google.co.in/citations?user=GyTmiXIAAAAJ&hl=en

◦ IIT Kanpur: Reach out to Bharat Bhushan and Janakarajan Ramkumar. They have conducted extensive research on the simulation of ISF for titanium (Ti-6Al-4V) and aluminum alloys, particularly regarding forming forces and step-depth optimization.

◦ IIT Madras (Chennai): Contact the research team including Srivardhan Reddy Palwai and Hariharan Krishnaswamy. They recently developed a novel frequency-based approach for designing preform shapes in multi-stage roboforming to enhance forming depth.

◦ NIT Tiruchirappalli: Connect with Chinnaiyan Sathiya Narayanan. His team is leading research into using patient-specific data to generate toolpaths for custom medical implants using ISF.

◦ IIT Guwahati: Uday Shanker Dixit is a key figure in numerical modeling for ISF processes in India.

People to hire or get advice:

https://www.linkedin.com/in/narayana-murty-svs-b88b515a

Based on the sources, here are the top academic and technical experts in India you should consider for your team or as strategic consultants:

1. Specialists in Roboforming & Robot Accuracy

Since 12-foot parts are highly susceptible to robotic deflection (robots being ~98% less stiff than CNC machines), these individuals are critical for modeling stiffness and accuracy:

• Prof. Hariharan Krishnaswamy (IIT Madras): A lead researcher in robot-assisted incremental forming. He pioneered the use of Fast Fourier Transform (FFT) for preform design, which enhances forming depth by up to 235% for complex shapes like cranial implants.

• Dr. Riby Abraham Boby (IIT Jodhpur): Expert in kinematic identification and elasto-static parameter modeling. His work is vital for reducing robotic end-effector errors by identifying and compensating for link and joint compliance.

• Dr. Eldho Paul (Mar Athanasius College of Engineering): Collaborator on major roboforming studies, specifically focusing on the Lumped Stiffness Model to accurately predict path deviations under high forming loads.

2. Experts in Strategic Materials & Heat-Assisted Forming

Forming titanium and refractory alloys at 12-foot scales requires precise thermal management to ensure ductility without oxidation:

• Prof. Janakarajan Ramkumar (IIT Kanpur): A leading voice in Induction Tool Heated ISF (ITHISF). His research demonstrated a 42% reduction in peak forming forces by heating the tool itself rather than the entire sheet.

• Dr. Bharat Bhushan (IIT Kanpur): Specialized in the numerical modeling of complex shapes on Ti-6Al-4V. He has extensive experience in simulating induction heat assistance to enhance formability in high-strength alloys.

• Dr. Seikh Mustafa Kamal (Tezpur University/IIT Guwahati): Expert in thermal autofrettage and electrically-assisted manufacturing, which are critical for inducing beneficial residual stresses in strategic components.

3. AI, Soft Computing & Computational Foundations

For a “software-defined” factory, you need experts who can integrate AI into the manufacturing workflow:

• Prof. Uday Shanker Dixit (IIT Guwahati): A central figure in computational foundations for metal forming. His work integrates Finite Element Method (FEM) with soft computing to predict forming forces and thickness with less than 5% error.

• Prof. Puneet Tandon (IIITDM Jabalpur): Lead researcher on the application of Artificial Intelligence in incremental forming. He has reviewed and developed AI techniques like neural networks and genetic algorithms for predicting springback and toolpath strategies.

• Dr. Prashant Kumar Jain (IIITDM Jabalpur): Specialized in the development of expert systems and the use of deep learning to capture and reuse manufacturing knowledge as “digital tooling”.

4. Production & Strategic Application Experts

For the specific verticals of DRDO defense projects and custom medical implants:

• Prof. Chinnaiyan Sathiya Narayanan (NIT Tiruchirappalli): A specialist in patient-specific titanium implants. He developed the patented Multi-Point Incremental Forming (MPIF) tool, which uses rotating balls to improve surface finish and formability in medical-grade alloys.

• Dr. Vamsi Krishna Balla (CSIR-CGCRI Kolkata): Expert in bioceramics and metal fused filament fabrication, offering deep insight into the metallurgical integrity of titanium alloys for high-stress applications.

Strategic Hiring Strategy for Your Idea Stage

• The “Architect”: Hire someone like Sahil Bharti (IIT Madras), who has experience in the systematic analysis of geometric inaccuracies and has published extensively on both the numerical and experimental sides of roboforming.

• The “Software Lead”: Look for students or associates of Aniket Nagargoje, who focused on feature extraction and toolpath generation using clustering algorithms like DBSCAN.

Metal which we can work:

1. High-Performance Strategic Alloys (Aerospace & Defence)

These materials are critical for the Indian defence corridors and DRDO initiatives, particularly for extreme-environment hardware.

• Titanium Alloys (Ti-6Al-4V, Grades 1, 2, & 5):

◦ Applications: Used for missile skins, hypersonic vehicle structures, aircraft engine components, and satellite parts where a high strength-to-weight ratio is mandatory.

◦ Medical Benefit: Ideal for patient-specific medical implants (cranial, maxillofacial, and dental) due to its bio-inertness and osseointegration properties.

• Nickel-Based Superalloys (Inconel 625 & 718):

◦ Applications: Essential for missile bodies, turbine discs, and exhaust structures that must maintain structural integrity under intense thermal and mechanical stress.

• Refractory Alloys (Niobium C103, Haynes 230):

◦ Applications: Targeted for the skins of hypersonic test vehicles because they can withstand the extreme temperatures generated during high-mach flight.

2. Lightweight Structural Alloys (Automotive & E-Mobility)

Targeting the rapid prototyping needs of Indian EV startups and aerospace primes.

• Aluminum Alloys (2xxx, 5xxx, 6xxx, 7xxx Series):

◦ Applications: Used for EV battery enclosures, chassis components, body-in-white panels, and aircraft fuselage sections.

◦ Benefit: Roboforming handles precipitation-hardened alloys (like 7075) effectively by forming them in a ductile state and applying post-process heat treatments to achieve peak strength.

• Magnesium Alloys (AZ31):

◦ Applications: Used for extreme lightweighting in automotive parts and biodegradable biomedical implants.

3. Industrial & Precision Engineering Materials

Used for large-scale, low-volume fabrication where traditional tooling costs are prohibitive.

• Specialty and Stainless Steels (304, 304L, 316, 316L):

◦ Applications: Used for automotive exhaust systems, mufflers, high-pressure piping, and food-processing equipment.

• Low Expansion Alloys (Invar 36):

◦ Applications: Critical for precision satellite structures and high-accuracy tooling where the material must not change shape during temperature swings.

• Copper and Copper Alloys (Brass, Bronze):

◦ Applications: Used for electrical stator bars, heat exchangers, and specialised marine hardware where high conductivity and corrosion resistance are required

Revenue:

Defense & DRDO:

◦ Indigenisation Projects: The Defence Research and Development Organisation (DRDO) is a primary candidate. Your technology directly supports “Atmanirbhar Bharat” by enabling the rapid fabrication of thin-walled skins for missiles, satellite structures, and hypersonic vehicles.

◦ Defense Corridors: Target firms operating in the Tamil Nadu and Uttar Pradesh defense corridors, which are receiving significant investment for new machining cells and aerostructures.

• Aerospace (Civil and Military):

◦ Hindustan Aeronautics Limited (HAL): They have already engaged with smart manufacturing training and are a potential partner for high-performance aerostructures.

◦ New Space Startups: Companies building satellites and launch vehicles often require specialized, lightweight titanium parts (like toroidal tanks) where traditional dies are cost-prohibitive.

• Healthcare (Custom Implants):

◦ Surgeons and Specialized Hospitals: Your first commercial revenue might come from fabricating patient-specific titanium cranial or orthopedic implants. ISF can produce these in hours using scan data, a critical advantage for trauma cases.

• E-Mobility (Automotive R&D):

◦ EV Startups and Premium OEMs: Companies like Tata Motors or Mahindra (who are already adopting hot forming for BIW components) may use your services for the rapid prototyping of lightweight aluminum battery enclosures and chassis components

Investors: anchor order from HAL/Indian Navy and strategic investment from L&T or Tata would be the fastest path.

Hyperbolic Metal Forming: https://www.shoesmachines.com/hyperbolic-metal-sheet-forming-machine

This device or tool is not doing this only by pressing. It uses energy from acoustics to vibrate each surface against the opposing pin surface. It is akin to “Ultrasonic Welding” but using the vibrational energy to hammer the metal in between the pins.
Imagine this action with a hammer used by a horseshoe maker with heated metal.
The responses by readers shows how each person sees things. Some see this an mesmerizing. Some see it as clever. Some see it as a new invention. I see it as simple physics but automating a simple principle - ultrasonic vibrational shaping.

Phase 1: Start with Roboforming (0-3 years)

Why?

Lower capital barrier to entry
IITs already have working knowledge
Can leverage India’s IT/AI strength
Defense aircraft repair is immediate use case (HAL, IAF depots)
Machina Labs model is proven — can be adapted

Action Items:

Create a dedicated startup (or DRDO/HAL spinoff) focused on roboforming
Partner with IIT Kanpur/BHU to commercialize existing research
Target HAL for aircraft skin repair/prototyping (like US Air Force + Machina Labs)
Build AI/ML capability for real-time forming compensation

Estimated Investment: ₹50-100 crore for first 3 years

Phase 2: Develop HMF/MPF for Shipbuilding (3-7 years)

Why?

India has ₹2.3 lakh crore naval modernization pipeline
60+ naval vessels under construction — massive potential
Chinese/Korean shipyards use MPF; India still uses manual line heating
Can leapfrog to competitive position

Action Items:

Technology transfer from Jilin University (China) or Korean institutes — or reverse engineer
Pilot at Cochin Shipyard or GRSE — modernization budgets are available
Develop indigenous MPF machine with Indian CNC/hydraulic manufacturers
Target architectural/construction market as secondary (hyperbolic facades are growing)

Estimated Investment: ₹200-500 crore over 5-7 years

Phase 3A: Hybrid Manufacturing Integration (Years 7-10)

The Core Concept: Combine Additive Manufacturing (AM) + Roboforming + HMF/MPF into a single integrated cell that can produce complex parts impossible with any single technology.

Why This Matters

Single Technology	Limitation	Hybrid Solution
Roboforming	Can’t add features, slow	AM adds ribs/bosses → Roboforming shapes
MPF	Surface defects, no fine features	AM prints functional features post-forming
3D Printing alone	Slow, expensive, size-limited	Form base structure → AM adds complexity
Stamping	Needs expensive dies	Eliminated with hybrid flexible approach

Technical Integration Pathway

┌─────────────────────────────────────────────────────────────────┐
│                    HYBRID FORMING CELL                         │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│   [Sheet Metal Input]                                           │
│          ↓                                                      │
│   [Roboforming / MPF] ──→ Base 3D Shape                        │
│          ↓                                                      │
│   [DED / WAAM*] ──→ Add ribs, bosses, reinforcements           │
│          ↓                                                      │
│   [Robotic Trimming / Drilling]                                 │
│          ↓                                                      │
│   [3D Scanning + AI Quality Check]                              │
│          ↓                                                      │
│   [Finished Hybrid Part]                                        │
│                                                                 │
│   *DED = Directed Energy Deposition                             │
│   *WAAM = Wire Arc Additive Manufacturing                       │
└─────────────────────────────────────────────────────────────────┘

India’s Existing Capabilities to Leverage

Capability	Current State	Phase 3 Integration
Wipro 3D	Metal AM for aerospace (HAL, ISRO)	Core AM partner
Godrej Aerospace	ISRO components, precision manufacturing	Integration expertise
IIT research	ISF, forming simulation, FEA	R&D backbone
L&T, Tata	Large-scale manufacturing, defense contracts	Scale-up partner
Objectify Technologies	AM services for DRDO, IAF	Defense qualification

Target Applications

Aircraft Structural Components
- Wing ribs with integrated stiffeners
- Fuselage sections with mounting bosses
- Landing gear components
Shipbuilding
- Hull sections with integrated pipe flanges
- Bulkhead panels with reinforcement ribs
- Complex curved surfaces with attachment points
Space
- Satellite bus structures
- Rocket tank domes
- Thrust chamber components

Phase 3B: AI-Enabled Autonomous Forming (Years 8-12)

The Vision: A forming cell that learns, adapts, and self-corrects in real-time — no human intervention needed for routine production.

Key Technology Components

Component	Function	Current State	India’s Path
Digital Twin	Virtual replica of physical system	Siemens, Hexagon lead	Partner with TCS, Infosys for indigenous solution
Generative AI	Design optimization, parameter prediction	OpenAI, NVIDIA dominate	Leverage India’s AI talent pool
Predictive AI	Springback compensation, defect prediction	Academic research stage	Commercialize IIT algorithms
Agentic AI	Autonomous decision-making, self-correction	Emerging globally	First-mover opportunity
Computer Vision	Real-time quality inspection	Mature technology	Integrate with forming cell

The Autonomous Forming Cell Architecture

┌──────────────────────────────────────────────────────────────────────┐
│                    AI-ENABLED AUTONOMOUS FORMING CELL                │
├──────────────────────────────────────────────────────────────────────┤
│                                                                      │
│  ┌─────────────┐     ┌─────────────┐     ┌─────────────┐            │
│  │   DIGITAL   │     │   PHYSICAL  │     │    EDGE     │            │
│  │    TWIN     │◄───►│    CELL     │◄───►│     AI      │            │
│  │  (Cloud)    │     │  (Factory)  │     │  (On-site)  │            │
│  └─────────────┘     └─────────────┘     └─────────────┘            │
│         │                   │                   │                    │
│         ▼                   ▼                   ▼                    │
│  ┌─────────────────────────────────────────────────────────┐        │
│  │              CAPABILITY STACK                            │        │
│  ├─────────────────────────────────────────────────────────┤        │
│  │ • Generative AI: Optimal tool path generation           │        │
│  │ • Predictive AI: Springback compensation in real-time   │        │
│  │ • Computer Vision: Defect detection mid-process         │        │
│  │ • Agentic AI: Autonomous parameter adjustment           │        │
│  │ • Reinforcement Learning: Continuous improvement        │        │
│  └─────────────────────────────────────────────────────────┘        │
│                                                                      │
│  INPUT: CAD file + Material spec                                     │
│  OUTPUT: Finished part (no human intervention)                       │
│                                                                      │
└──────────────────────────────────────────────────────────────────────┘

Why India Can Win Here

Advantage	Explanation
IT/Software talent	World’s largest pool of AI/ML engineers
Cost arbitrage	Develop at 1/5th the cost of US/Europe
Captive demand	₹2.3 lakh crore naval pipeline + HAL + ISRO
Leapfrog opportunity	No legacy systems to replace
TCS/Infosys/Wipro	Can build Digital Twin platforms

Investment: ₹500-800 crore over 4 years Model: Joint venture between IT major (TCS/Infosys) + Manufacturing partner (L&T/Tata) + Research (IITs)

Phase 3C: The Export Play — “Forming-as-a-Service” (Years 10-15)

The Ultimate Goal: India becomes a global exporter of forming technology and forming services — not just formed parts.

Three Export Models

Model 1: Technology Export (Hardware + Software)

Sell complete autonomous forming cells to other countries
Target: Southeast Asia, Africa, Middle East, Latin America
Compete with Chinese MPF machines at higher quality tier

Model 2: Forming-as-a-Service (Cloud Manufacturing)

Customer uploads CAD → India’s factory produces → Ships globally
Like Machina Labs but at India cost structure
Target: Aerospace Tier-2/3 suppliers globally, shipyards

Model 3: Deployable Microfactories

“Factory-in-a-container” — ship complete forming cell to customer site
Operate remotely from India via Digital Twin
Target: Defense installations, remote shipyards, disaster response

╔═══════════════════════════════════════════════════════════════════════════╗ ║ INDIA ADVANCED FORMING ROADMAP ║ ╠═══════════════════════════════════════════════════════════════════════════╣ ║ ║ ║ PHASE 1: ROBOFORMING (0-3 years) Investment: ₹50-100 Cr ║ ║ ┌─────────────────────────────────────────────────────────────────────┐ ║ ║ │ • IIT commercialization → Startup │ ║ ║ │ • HAL anchor customer (aircraft repair/prototyping) │ ║ ║ │ • Build AI/robotics capability │ ║ ║ │ • Outcome: Working roboforming cells at 2-3 defense sites │ ║ ║ └─────────────────────────────────────────────────────────────────────┘ ║ ║ │ ║ ║ ▼ ║ ║ PHASE 2: HMF/MPF (3-7 years) Investment: ₹200-500 Cr ║ ║ ┌─────────────────────────────────────────────────────────────────────┐ ║ ║ │ • Technology transfer or indigenous development │ ║ ║ │ • Pilot at Cochin Shipyard / GRSE │ ║ ║ │ • Develop springback compensation algorithms │ ║ ║ │ • Outcome: MPF machines at 2+ shipyards, architectural projects │ ║ ║ └─────────────────────────────────────────────────────────────────────┘ ║ ║ │ ║ ║ ▼ ║ ║ PHASE 3: AUTONOMOUS HYBRID FORMING (7-15 years) Investment: ₹800-1300 Cr║ ║ ┌─────────────────────────────────────────────────────────────────────┐ ║ ║ │ 3A: Hybrid AM+Forming integration │ ║ ║ │ 3B: AI-enabled autonomous cells (Digital Twin, Agentic AI) │ ║ ║ │ 3C: Export play — Technology, FaaS, Microfactories │ ║ ║ │ • Outcome: $3 - 4 bi ll i o n e x p or t ma r k e t, g l o ba lt ec hn o l o g y l e a d er │║║ └ ───────────────────────────────────────────────────────────────────── ┘ ║║║║ TOT A L I N V ESTMENT : ₹1, 050 - 1, 900 C rore ($ 125-225 million) over 15 years ║ ║ POTENTIAL OUTCOME: $3-4 billion annual exports by 2040 ║ ║ ║ ╚═══════════════════════════════════════════════════════════════════════════╝

Phase 4:

Start producing titanium baby!!!

FFC_Cambridge_process: https://en.wikipedia.org/wiki/FFC_Cambridge_process

Rupen

Sun, 01 Mar 2026 17:29:59 GMT

https://www.reddit.com/r/godot/comments/s5axub/i_created_a_python_program_to_automatically/

https://x.com/startracker/status/2012934529288487070

social media:

Whatsapp
Youtube
Instagram
Web
twitter
Tiktok/Douyin
Weibo
Japan(twitter is great go to market here)
Chinese
Europe

SEO and AI/ML

rive kind of editor where individual things can be edited manually and if wanted prompted also like a sexy intuitive UI
reference based design, context matters, brand kits, add yt video and design the thing like that
figma direct integration
state machine to make the design and animation more sexy and more predictable
fork and create more variations, similar philosophy like ntoplogy
SDK integrations for other platform(react native, JS, flutter, unity, web etc…)
temp scratch pad with segment anythign and yolo thing to remove things, sota art all kinds of model integrated

things to use:

don’t use video model directly cause it will be not that good for editing individual things
https://github.com/QwenLM/Qwen-Image-Layered

Success metrics:

The 5-Second Rule: in 5 second they should see the value!
Version Control:
- Let users fork/snapshot before AI regeneration
- This reduces fear of “losing” manual edits
Hybrid Prompting:
- “Change the blue circle to red” should be instant
- “Make it feel more energetic” triggers AI
- Clear distinction between direct edits vs. AI interpretation

will need this kind of mockups so people can make sexy videos intro videos or animations which i always see in the launch videos:

https://wannathis.one/

later adding text to 3d and then animating it using huyen tencent to give more control and idea and unleash the creativity
removing background from images and enhancing it more

project MG15

Sun, 01 Mar 2026 17:29:59 GMT

I want to build more hardware projects and more sci fi stuff and push them to the limits and commercialise them on crazy scale, like kick starter is our playground kind of thing,

base line or what this guy is doing is great starting point but need to become more than just toys:

https://www.youtube.com/@HTXStudio/shorts

Minecraft Robot Self driving skateboards trained on RL and CV models

shadowfax

Sun, 01 Mar 2026 17:29:59 GMT

https://store.steampowered.com/app/2365790/Lets_Build_a_Dungeon/

https://github.com/clawdbot/clawdbot?tab=readme-ov-file

the thing should also punish for generating a slop!

https://github.com/EveryInc/compound-engineering-plugin

this guys are always on sota: https://seed.bytedance.com/en/ https://qwen.ai/research

i really liked the aesthetics of every and umns: https://un.ms/ https://every.to/

the thing which every is doing is great, it is what exactly kind of things we want to go for: https://makeitsparkle.co/

we can use this info and create things around them and sell it: https://x.com/systematicls/status/2004900241745883205

affilate marketing

ultimate project to push all the boundaries and limits of what is possible:

Simple idea is to automating and making living company just using AI agents, and one coder infra and intial things to kick start or like automating indie hacking

i really like this kind of clean and trust building websites: https://tryholo.ai/

https://x.com/ID_AA_Carmack/status/1921967025628578230 need to think about this

tech stack:

nue: https://nuejs.org/ (for the simpler and easy things which doesn’t need any specific heavy backend use, wasm is there to rock the world)
Laravel (main backend using react as frontend)
R2 for blob storage
Aiven or supabase database (in starting the manual deployment then probably see the pricing and how to automated it)
for Ai related and agents which will be used in the application(https://developers.cloudflare.com/agents/)
https://github.com/abshkbh/arrakis for sandboxing and making the agents go crazy

deployment:

https://vapor.laravel.com/

or for the intial deployments:

http://cloud.laravel.com/

main goal is to make auto evolving organism(https://truthseekermusings.beehiiv.com/p/company-organism)

Brahma, Vishnu, Mahesh framework

will add the more minor resources and tweaks to make them a god like at their individual task

my office people:

CEO:

I am the CEO bitch, there will be management CEO, who will see the all things, and run the system perfectly, where things are getting slow, and making sure everything is there how it is need to be and where the whole things is going on, taking the decision on the basis of the all the available information, input, output and outcome
and i am the main mentor for the CEO, which he discuss the mostly things of what we are going or headed

CTO:

main goal or task of the CTO is to make the infra and current tech stack and things, making very easy to keep the current functions and things running easily, identifying all the bottlenecks from tech pov, and making sure the quality of code is really maintainable and communicating with other SRE and R&D to push the things on the tech level, and making sure to get things done, he will get his hands dirty where he needs to be
building tools to things more easily, shipping something which makes shipping more faster itself
his one more thing or task is to standardise things, like if we need newsletter and mailing tech, observing and automating things or deploying and developing standard processes, tools

Product Manager:

product managers task is to get complete the product, products ownership is his/her, the end quality of the features and product and intent of the things and delivering the polished feature to the end one
will manage interns, developers, and will coordinate between different developers frontend engineer designer and other things
following KPIs and tracking other things, and on the based on the data taking and understanding and shaping the next steps for the app
Resources:
“The Mom Test” by Rob Fitzpatrick
Lenny’s Newsletter
Shreyas Doshi’s Twitter Threads
“Inspired” by Marty Cagan

Designer:

this guy is frontend wizard, and not only he can design crazy thing but also create prototype and if needed can go and integrate also
really clean, loved and care for craft kind of designs
need to teach great taste to this guy
this guy also need to understand the context and the goal and consumer profile and design accordingly
Resources:
https://animations.dev/
https://x.com/BrettFromDJ

Marketer/copywriter:

this guys main work is to be great story teller which is authentic and great copywriting
he needs to understand the trends and all the good things
i lack knowledge about this area so need to learn and understand this more
Resources:
Seth Godins book

Community Builder:

community and making fans is really way to building a long lasting and great product
this guys job is to inform and play the role of https://x.com/OfficialLoganK
helping people and making them feel satisfied, and taking the initiatives
will communicate back to the other team about what people are thinking or how they are feeling about it

Distribution Builder:

this guys main job is to find out and setup the main distribution channel
monitor the existing channels and do whatever needs to do to push more and grow
merging existing channels, trends and all that

SRE:

this guys main job is to make the whole system running as smooth as fuck
making self healing systems
this will not get involved in to specific product or like that but focuses on more on the whole system and network of things
task is how to create a system which helps us create more self healing agents, that level of infra

Researcher:

this guys main goal is to find the new trends, upcoming trends, high roi research keywords which are really can be montized
this guy needs to be street smart, reading from reddit comments to forums to everything
mining all the great ideas and giving them with all the information
main idea guy and market validator or exist kind of goal
if he thinks or wants to check, he goes and creates a reddit post something like that

R&D:

this guy is our AI/ML researcher, or tech influencer kind of guy
who will see what is new in the field, build prototypes, how things can be improved and help in integrate this new things in our existing products and what new kind of products will be possible

Finance guy:

he will not be here yet, but main person responsible for all the financial related stuff, from giving access to money to other people

need to think about feedback loops connecting all agents in one network while still keeping the privacy and silo kind of communication will figure out things

and building all of those individual profile and pushing towards build in public more, and like total game changer thing, like fuck this is going to really cool, it’s like ai agent having a proper proper life

another problem is over communication and too little communication

fuck this guyes will have their own website, we are making a society kind of

in many places agents will be suspended so will need humans who will help them to get job done, many time manual work, posting on some platform where lot of bot protection or spam protection is there, also needs some good kickass video editor and content guyes, like where ever agents feel shorter and limited, he employs humans to get work done, need money to make this happen

i know all can’t be automated, but above roles are generally defined, it will have more parts more agents under them to do perfect and specific task

https://docs.google.com/spreadsheets/d/1z6_WN7XYngyJd-kKSHcmKxSKVFpf4dV8RbUofUdTQ9c/edit?gid=90745215#gid=90745215

https://good.services/the-good-services-scale

resources:

Karan's Notes

Daily Routine

The System

Saturday AM Override

Sunday Override

The Rules

Tinker Hour Rotation

2025-2026

projects:

Books:

Skills:

goals/metrics:

companies on the radar(grab opportunity if given or create):

Adventure & Explore

Social & Human Connection

functional programming

hardcaml FPGA

The Core Idea: Tracing vs. Building

What This Buys Over HardCaml Specifically

Comparison Across the Ecosystem

The Clash Comparison Is Central

The Dart Angle

What Would Genuinely Be Novel

What Makes a Good Test Case

Tier 1: Best Bang for Effort

A Systolic Array for Matrix Multiply

A Pipelined RISC-V Core (RV32I)

Tier 2: Sharper Tests of Specific Effect Properties

A Parametric FIR Filter Bank

A SHA-256 / AES-128 Core

A UART / SPI Controller

Tier 3: Ambitious / Research-Grade

A Sparse Attention Accelerator

Connecting to OpenROAD / Yosys

Concrete Recommendation

kids metal songs

self balancing music player

GC-Fuzz

Rex-Minecraft Robo Dog

writing

8th April 26

Co2 Remove

sabbatical stuff

Game Studio

Journey to the cool

ecommerce-os

gc-rust

Incremental Sheet Forming

Market Validation Questions

Technical Validation Questions

Unit Economics Questions

Competition Questions

Go-to-Market Questions

Phase 1: Start with Roboforming (0-3 years)

Phase 2: Develop HMF/MPF for Shipbuilding (3-7 years)

Phase 3A: Hybrid Manufacturing Integration (Years 7-10)

Why This Matters

Technical Integration Pathway

India’s Existing Capabilities to Leverage

Target Applications

Phase 3B: AI-Enabled Autonomous Forming (Years 8-12)

Key Technology Components

The Autonomous Forming Cell Architecture

Why India Can Win Here

Phase 3C: The Export Play — “Forming-as-a-Service” (Years 10-15)

Three Export Models

Rupen

project MG15

shadowfax