Vyom Pathak 01-vyom
- San Francisco, USA
- 01-vyom.github.io
- in/01-vyom
- @vyomp01
Organizations
@developer-student-clubsStars
Fast and memory-efficient exact kmeans
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
[ICML 2026] An Evaluation Suite for Chain-of-Thought Controllability
Research artifacts from Recursive's automated AI research system
autonomous nanogpt optimizer speedrun
Code to automatically prove or verify estimates in analysis
Open-sourced evaluation suite from the Monitoring Monitorability paper
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
Fault tolerance for PyTorch (HSDP, LocalSGD, DiLoCo, Streaming DiLoCo)
Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.
AI agents running research on single-GPU nanochat training automatically
A lightweight inference engine supporting speculative speculative decoding (SSD).
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.
Anthropic's original performance take-home, now open for you to try!
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.
Simple, unified interface to multiple Generative AI providers
Analyzing Hacker News discussions from a decade ago in hindsight with LLMs
LLM Council works together to answer your hardest questions
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Helpful tools and examples for working with flex-attention