Agents
The Bitter Lesson for harness design and formal math! Instead of hand-designing how an AI should prove (decompose, plan, assign agents), wha…
The Bitter Lesson for harness design and formal math! Instead of hand-designing how an AI should prove (decompose, plan, assign agents), what if we just give a frontier model good Lean feedback and le
The Bitter Lesson for harness design and formal math! Instead of hand-designing how an AI should prove (decompose, plan, assign agents), what if we just give a frontier model good Lean feedback and let it keep working? We built h1. TL;DR: → SOTA on formal theorem proving benchmarks → can solve open conjectures → matches/beats hand-designed workflows → one long attempt can beat many retries [1/7]
Related
- The Harness should be Model agnostic. The Knowledge it builds around you is your moat. You should not have to migrate or give that up just b…
- the “harness” will never go away, and it’s just as important as the model
Source: Yohei Nakajima (X) | 2026-10-12