Learning Beyond Gradients

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

saved by

• Davis Brown
• Vihan Tiwari
• Christina Lee

related reading

• Composer2.pdfcursor.com
• Discovering 108 tricks to accelerate grokkingkindxiaoming.github.io
• 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
• Deep Reinforcement Learning: Pong from Pixelskarpathy.github.io
• State of RL for reasoning LLMs | A. Weersaweers.de
• Deep Reinforcement Learning: Pong from Pixelskarpathy.github.io
• Why We Need Continual Learning | Andreessen Horowitza16z.com
• Michele Catasta (@pirroh) on Xx.com
• [1707.06347] Proximal Policy Optimization Algorithmsarxiv.org
• pistar06.pdfpi.website
• Welcome to Learn Harness Engineeringwalkinglabs.github.io