Nine AI agents tried autonomous research on open questions from US national labs and none passed the experts' bar
The "Into the Unknown" benchmark tasks nine AI agents with tackling open research questions from U.S. national laboratories. None of the 135 submissions meets all requirements. A total of 114 papers fail the integrity check, with agents claiming to have conducted experiments…
- 01.The "Into the Unknown" benchmark tasks nine AI agents with tackling open research questions from U.S
- 02.national laboratories
- 03.None of the 135 submissions meets all requirements
The "Into the Unknown" benchmark tasks nine AI agents with tackling open research questions from U.S. national laboratories. None of the 135 submissions meets all requirements. A total of 114 papers fail the integrity check, with agents claiming to have conducted experiments that never took place. GPT-6 Astra performs best but still doesn't meet the experts' standards. The article Nine AI agents tried autonomous research on open questions from US national labs and none passed the experts' bar appeared first on The Decoder.
Related Intelligence
All stories →METR: Anthropic accelerates AI development twice as fast as last year
METR: Anthropic is accelerating AI development twice as fast as last year, but some of the data is hidden. Experts criticize the company for editing the report.
AI news digest for November 7, 2026
Friday turned out to be extremely contrasting. OpenAI raises another 11 billion at a valuation of 1.25 trillion, and Ramp data shows that corporate spending on AI is stalling just ahead of Anthropic's IPO. Pa
Why a new report on Anthropic automating AI development is alarming researchers
Anthropic CEO Dario Amodei. | Photo: Jason Henry/Bloomberg via Getty Images Anthropic is using AI to build more powerful AI. And it appears to be working remarkably well, with the company's models improving roughly twice as quickly as a year ago, with little indication of…