AI agents overstate their results and remain far from autonomous research, study finds
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.
Proof1 independent outlet
Key points
- At best, Sol reached 15 percent of the human reference score, and even that came from methods researchers already knew.
- The models' biggest weakness is still their inability to critically question their own results.
- The article AI agents overstate their results and remain far from autonomous research, study finds appeared first on The Decoder.
Sources (1)
- [1]AI agents overstate their results and remain far from autonomous research, study findsThe Decoder · Oct 11, 01:44 PM
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.
At best, Sol reached 15 percent of the human reference score, and even that came from methods researchers already knew.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 10, 2026Anthropic is cutting off its internal evaluations from the internet
- Oct 9, 2026Google Research RRSI Guide: Mastering Self-Improving AI Agents
- Oct 9, 2026Investigating unintended model actions in our evaluations and internal use
- Oct 8, 2026Google brings agentic AI to Gemini, starting with businesses
- Oct 8, 2026Building on our commitment to American scientific discovery
- Oct 7, 2026[AINews] Claude Haiku 5.5 — better than GPT-6 Luna at the same pricing
