✳flâneur — a map of the web's best reading
Learning Beyond Gradients
trinkle23897.github.io · 5,784 words · saved by 3 readers
Learning Beyond Gradients
Learning Beyond Gradients Jiayi Weng Continual Learning has remained hard largely because of catastrophic forgetting in neural networks: learn something new, and old capabilities can get overwritten. But what if we do not put all of our attention on neural network weights? Is there another way to make progress? As LLM agents get stronger, coding gets faster and better. But the phenomenon I find more interesting is different: a coding agent can keep reading failures, editing code, adding tests, and watching replays, and a program system can improve without training a new network or updating wei
Explore this link on the map →saved by
related reading
- Composer2.pdfcursor.com
- 1b44b878bb782e6954cd888628510e90-Paper-Conference.pdfproceedings.neurips.cc
- Andrej Karpathy — AGI is still a decade awaydwarkesh.com
- The 37 Implementation Details of Proximal Policy Optimization · The ICLR Blog Trackiclr-blog-track.github.io
- Debugging Reinforcement Learning Systemsandyljones.com
- State of RL for reasoning LLMs | A. Weersaweers.de
- A vision researcher’s guide to some RL stuff: PPO & GRPO - Yuge (Jimmy) Shiyugeten.github.io
- State of Robot Learning, December 2025vedder.io
- NL.pdfabehrouz.github.io
- Why We Need Continual Learning | Andreessen Horowitza16z.com
- Deep Reinforcement Learning: Pong from Pixelskarpathy.github.io
- Effective harnesses for long-running agents \ Anthropicanthropic.com