Anthropic's Autonomous Alignment Researcher beats humans 7/7 at $4/hour
daniel_mac8 · x · 2026-08-30
Anthropic published research on an Autonomous Alignment Researcher powered by Claude Opus 4.8:
- Beat human AI researchers on 7/7 experiments;
- API inference cost of roughly $4/hour vs. $150/hour for a human researcher;
- Notably, runs seeded with human-expert direction performed no better than when Opus 4.8 chose its own direction.
The poster quipped: "Recursively self-improving ASI is here, it's just not evenly distributed."
Related event: Anthropic's Autonomous Alignment Researcher Outperforms Human Experts(22 posts)→
More from Safety
- FTC subpoenas Anthropic and OpenAI over safety incidents and consumer protection concerns — asusarla · 2026-10-16
- Anthropic red team's first-ever model "abliteration" cut GLM-5.3 refusals from 90% to 3% for ~$4,400 — cephaloform · 2026-10-16
- Anthropic grants METR employee-like access as independent safety evaluators go public — AnthropicAI · 2026-10-16
- APEX-Harm benchmark: script-based injection attacks easily compromise agents in shared workspaces — KAUST · 2026-10-16
- Residual-stream forecasts predict agent violations before they happen, USC study shows — USC · 2026-10-16
- Blogger doubles down: Anthropic's Scion image model accused of ripping off Mononoke — sunshowers · 2026-10-16