Épi self-evolving research framework nets 120 record results in days
my_cat_can_code · x · 2026-09-14
Bake AI introduced Épi, a self-evolving framework for autonomous research combining verifiable environments, agents that design and test their own approaches, and sandbox infrastructure for large-scale parallel experiments.
Within days, Épi produced 120 record-setting results across mathematics, quantum information, operations research, and engineering optimization — 20 numerical bound records and 100 construction records — plus a proof extending a special case of Tuza's conjecture.
The thesis: models provide capability, environments make progress verifiable, and Épi turns compute into cumulative improvement.
Related event: Self-evolving research framework Épi claims 120 record results in days(4 posts)→
More from coding & agent
- Devs compare working with Codex vs Claude Code to StarCraft races — Kangwook_Lee · 2026-09-14
- Open-source agent harness runs 63-hour autonomous Riemann hypothesis attempt on a single RTX 3090 — GuiltyBookkeeper4849 · 2026-09-14
- Agentic coding brings back human connection at this game studio, founder says — TAbrodi · 2026-09-14
- Clarifying the AI agent messaging drama: it just couldn't access a link — Kyrannio · 2026-09-14
- Cloud queue + local agent hits a wall: laptop off, all scheduled jobs die — PriorElephant9 · 2026-09-14
- Freelancer's Gmail task-extraction script worked — until the manual 'last mile' killed it — Thefounderman1 · 2026-09-14