“Retrying vs Resampling in AI Control” by james.lucassen, Adam Kaufman
Podcast:LessWrong (30+ Karma) Published On: Fri May 29 2026 Description: We’ve just released a new paper: Retrying vs Resampling in AI Control. We revisit the resampling protocols introduced in Ctrl-Z with an up-to-date setting and much stronger models, and compare them against “retrying” protocols similar to Claude Code auto mode or Codex Auto-review. Motivation Roughly a year ago we released Ctrl-Z, the first paper to study control techniques for agents. A headline result of that paper was the performance of resample protocols – strategies that involve taking multiple i.i.d. samples from the model per step. But since Ctrl-Z, models have gotten much stronger, and we have built more sophisticated control settings to keep up. We wanted to answer the following questions: How well do the results from Ctrl-Z hold up with better models and a better setting? Current high stakes control research is trying to learn by analogy about how to do control effectively in a real high stakes deployment during a real intelligence explosion. Findings about technique performance[1] are going to have to generalize pretty far to be useful. If the resample protocols from Ctrl-Z still work, what makes them work? One way we try to make our work more generalizable is by understanding the dynamics governing outcomes [...] ---Outline:(00:30) Motivation(02:36) TL;DR Takeaways(03:55) en-US-AvaMultilingualNeural__ Bar graph showing safety percentages across different monitoring and resampling methods.(04:36) Methodology(07:16) Differences from Ctrl-Z(12:11) Are Retrying Protocols Exploitable?(15:24) Cost and Latency of Resampling(17:22) Conclusion The original text contained 7 footnotes which were omitted from this narration. --- First published: May 29th, 2026 Source: https://www.lesswrong.com/posts/yThJQTJxtmKNeZGwA/retrying-vs-resampling-in-ai-control --- Narrated by TYPE III AUDIO. ---Images from the article:Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.