AI brief
Epoch AI and Anthropic independently found that current AI models can run experiments but lack scientific self-criticism and genuine creative thinking, with one model reaching at best 15 percent of the human reference score.
Why it matters: It suggests today's models remain far from conducting autonomous research despite being able to run experiments.
Written by AI from The Decoder's published text.
Background
From our own funding, model and news trackers, not from the source.
Anthropic
- Latest funding
- Growth · $65B · 28 May 2026
- Newest model on the API
- Claude Haiku 5.5 · 7 Oct 2026 · $0.1 in / $0.5 out per million tokens
Source
“Epoch AI and Anthropic independently found the same thing: current AI models like GPT-5.6 Sol and Claude Fable 5 can run experiments but lack scientific self-criticism and genuine creative thinking.”
Reporting from a publisher outside the organisation being covered.
Read original story ↗