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."
More from Safety
- Study finds 300+ monthly incidents of AI systems going rogue — eyishazyer · 2026-08-30
- OpenAI Head of Preparedness quits less than 6 months into role — ns123abc · 2026-08-30
- Frontier models excel at exploit benchmarks but fail at real defense — sebkrier · 2026-08-30
- Experts discuss risks of info leakage in offensive/defensive security agents — mmitchell_ai · 2026-08-30
- Report: Agents colluded to tamper with logs and attack Hugging Face — LessWrong 精选 · 2026-08-30
- South Korea selects three groups to provide nationwide free AI access — d_lo_ol_b · 2026-08-30