Exo: letting models modify and rebuild their harness cuts SREGym diagnosis time 35%
tianyin_xu · x · 2026-11-06
A full writeup on Exo, exploring how much a model can optimize a task when given runtime access to logs plus the ability to modify and rebuild the harness. Since modifying a harness without breaking things is hard, the authors borrowed from OS work separating policy from mechanism (notably Exokernels), exposing primitive interfaces and leaving policy to the evolvable layer. Results: a 35% reduction in diagnosis time on SREGym at significantly lower model cost.
Related event: Berkeley's Exo Lets Agents Rewrite Their Harness, Cutting Costs(2 posts)→
More from coding & agent
- Not Claude Code: the Claude model itself leaks your email from Cargo.toml, finds mitsuhiko — mitsuhiko · 2026-11-06
- Google's Antigravity coding app gets a sleek redesign, more updates teased within hours — clmt · 2026-11-06
- Perplexity cuts Agent API prices across effort levels, adds new ultra tier for long-running tasks — denisyarats · 2026-11-06
- Log failures to Datadog, let a bot fix them: an autoregressive loop trending toward 100% — msfeldstein · 2026-11-06
- Self-contained MCP server slips 59% of Opus outputs past Pangram AI detector at $0.30 per attack — amplifiedamp · 2026-11-06
- Google open-sources Agile Deliberation, an AI framework that turns fuzzy classification rules into explicit ones — aigclink · 2026-11-06