Skip to content
Synced · WeChat

OpenAI's Jiayi Weng: Is the Next AI Training Paradigm Beyond Gradients?

OpenAI翁家翌:梯度之外,下一个AI训练范式有着落了?

OpenAI researcher Jiayi Weng proposes Heuristic Learning: codex gpt-5.4 reached a perfect 864 score on Breakout and generated 342 search trajectories across Atari 57, with updates applied to code, tests, replays, and memory rather than neural-network weights.

Why it matters: OpenAI researcher Weng Jiayi proposes heuristic learning, where models improve by editing code, tests and memory rather than updating weights.

Read the original ↗Export Markdown