✳flâneur — a map of the web's best reading
Rajan Agarwal
rajan.sh · 237 words · saved by 2 readers
Notes, research, and projects by Rajan Agarwal.
Rajan Agarwal Rajan Agarwal I work on coding models at OpenAI , on leave from my undergrad at Waterloo. Recently I've worked with great people and teams at Thinking Machines , Proximal , Amazon AGI , Thoughtful Lab , and Cohere Labs . Reach out! I always want to meet more people with controversial opinions, fun stories and new ideas, or who want to play tennis. I am most active on: X GitHub Curius Scholar Notable Work Tiny Interaction Models ( Jun 2026 ) Post-training a small open model to read typing as a live stream: look things up mid-sentence, hold the result, stay quiet otherwise. Frontie
Explore this link on the map →saved by
related reading
- Arjun Virkarjunvirk.com
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- AINews | AINewsnews.smol.ai
- Inkling: Our Open-Weights Model - Thinking Machines Labthinkingmachines.ai
- Composer2.pdfcursor.com
- 2025: The year in LLMssimonwillison.net
- GitHub - karpathy/autoresearch: AI agents running research on single-GPU nanochat training automatically · GitHubgithub.com
- The 2025 AI Engineering Reading List - Latent.Spacelatent.space
- Building reliable AI agents · parth sareenparthsareen.com
- Claude Code Cheat Sheetcc.storyfox.cz
- What I learned building an opinionated and minimal coding agentmariozechner.at
- Don’t Outsource Your Thinkingteltam.github.io