← Back to People
Chenglei Si conducted a large human study finding that expert judges rated LLM research ideas above human ones, but human ideas worked better when executed.
1
Mentions
1
Articles
1
Outlets
Companies Covered
Articles
Most recent firstMentioned In
Referenced in coverage
Governing AI Agents: Alan Chan of GovAI on Monitoring, Agent IDs, Rogue Agents & Preparing for RSI
The Cognitive RevolutioncautiousOct 14, 2026
“Chenglei Si conducted a large human study finding that expert judges rated LLM research ideas above human ones, but human ideas worked better when executed.”