Study: AI Agents Cannot Yet Conduct Open-Ended AI Research
sebkrier · x · 2026-08-09
A new study suggests that AI agents are not yet close to recursive self-improvement (RSI), despite progress on narrow, verifiable tasks.
Researchers partnered with authors of two unpublished AI papers and tasked frontier AI agents with answering core research questions using thousands of dollars in API credits and six days of compute. The original authors ultimately rejected both agent-generated papers.
Log analysis revealed that agents lacked the judgment for open-ended research. While they occasionally proposed impressive directions, they typically rejected these ideas quickly based on low confidence.
More from AGI Musings
- Video Generation Is Booming, But Where Are the Deep Video Analysis Models? — Legitimate-Arm9438 · 2026-08-09
- Matt Turck: Tech Industry Shouldn't Ignore Resistance to AI Data Centers — mattturck · 2026-08-09
- Using Frontier Tokens to Generate Traces Compressed into Capital Assets — curious_vii · 2026-08-09
- FT Report Sparks Public Outcry Over AI Synthetic Virus Risks — NathanpmYoung · 2026-08-09
- Miles Brundage & Experts Release Comprehensive Guide on Frontier AI Third-Party Auditing — Miles_Brundage · 2026-08-09
- Debate: Will Vertical AI Giant Harvey Achieve AGI Faster Than Anthropic? — Shahules786 · 2026-08-09