Quick Links
hi i’m shubham attri,
i like trying things, know myself and acquire tooling to do so, thinking, reading, experimenting and being aware are some .
my dialogue with philosophy and the borrowed wisdom of people sharing true internal motivations.
i believe that world models will unlock more value than software, working on solving the problems of the physical world with the help of ai, to make it more accessible and intelligent at phi9.space.
previously worked on etheca to create valuable software, working on memory store to solve memory for agi.
also:
- building: Memory Store | RSI Lab | Sansara | Bestia Brisk
- x: a3fckx
- code: github.com/a3fckx
- email: a3fckx@proton.me
Recent Research
Agora CompactCTM Shadow — Stage-1 Prediction Without Control
Held-out CompactCTM shadow predictor fails to beat an empirical prior on Agora opinion-diffusion transitions; claim class is non-parity, control authority false, not promoted.
Five-Node Intervention Discovery
A preregistered three-seed pilot on five-node wave-causal circuits: the phase-cancelling circuit is real, but none of the acquisition-strategy superiority claims survived.
Continuous Thought Machines: A Research Atlas
A source-grounded dissection of Sakana AI's Continuous Thought Machines, paired with an inspectable parity protocol and an explicitly disputed local reproduction state.
Recent Writing
The Recipe for Solving Software
Recursive graph based agents with memory are the recipe for solving software. Everything else is distraction.
the intern problem
Why AI is like the world's smartest intern: brilliant but lacking tacit knowledge and context. The real unlock isn't smarter models—it's systems that remember.
Memory enabled Claude Code
Using memory store plugin with claude code for development