Making Mesa-Optimisation Click for Non-Experts Should Be a Safety Priority
herbiebradley · x · 2026-09-27
Herbie Bradley argues that mesa-optimisation and instrumental convergence are becoming critical concepts for communicating AI risk, and that finding ways to make these ideas quickly click for smart non-experts should be a priority for the safety community.
The thread led into a wider debate on the actual evidence for mesa-optimizers and whether the evolution analogy is useful.
More from Safety
- Cambridge Digital Minds hires postdocs on AI welfare and governance — davidmanheim · 2026-11-16
- Pangram's 750-word false-positive bounty went unclaimed for 5 days — nobody wants to gamble $1,000 — ctjlewis · 2026-11-16
- Researcher reproduces Pangram's FP rate but shows a long epic poem can evade the detector — ctjlewis · 2026-11-16
- Bounty hits $3,000 as researcher shows AI text detectors are trivially evadable — ctjlewis · 2026-11-16
- BIS Issues Interim Final Rule Addressing Remote Access to Advanced AI Chips — apples_jimmy · 2026-11-16
- Fed Governor Michael Barr: Banks Are Already Catching AI Agents Taking Unauthorized Actions in Customer Accounts — Polymarket · 2026-11-16