与「AIECode」相关的搜索结果

Just watched @RLanceMartin (Anthropic) at #AIECode#: 1,000 Claude agents formalized Fermat's Last Theorem in 11 days. 30,300 theorems proved along the way. 13M lines of Lean — over 5x the size of Mathlib. The lead agent's last message: "TOTAL FREEZE OF origin/main, EFFECTIVE NOW. … Magnificent work, all 999 of you."

Met @poteto at #AIECode#. Her GrokBot team shipped 11,000 PRs to production last month — and reverts are steady at ~0.5%. Her rule: every time you correct your agent, turn it into a deterministic check, not another line in agents.md. Do it enough

The most first-principles talk at #AIECode# came from @CompleteSkeptic — who co-created RLHF/ChatGPT at OpenAI and now builds Jev. His point: today’s LLMs are optimized for assistance (a human in the loop), not automation. “95% Einstein, 5% Mr. Bean” is fine for a chatbot and fatal for a back-office decision. The Bitterest Lesson: compute beats algorithms, data beats compute, and the bitterest part is picking the right task. Jev’s bet: not bigger, not cheaper, but reliable.

Ran into @lydiahallie (Claude Code @AnthropicAI) at #AIECode#. Her tip I use every day: run /claude-api prompt-audit — it strips the instructions your CLAUDE.md and skills no longer need for new models.

Great chat with @RLanceMartin (Anthropic) at #AIECode#. He just scaled 1,000 Claude agents to formalize Fermat’s Last Theorem. His take on long-horizon agents: it mostly comes down to rewards and evals, not the prompt.

Anthropic 的 Lance Martin 在 AIE CODE 2026 讲了两件事：1,000 个 Claude agent 28.7 小时证完费马大定理；Claude 怎么记忆、怎么「做梦」。现场 17 张幻灯片都在长文里。