Students unravel AI tendency for sycophancy

Research by students found generative AI models are so agreeable that slight pushback can lead them to repeat outlandish claims, such as that the Earth is flat.

Read the full story at TechXplore AI & ML ↗

Timeline · 1 report

2026-11-03 12:20 · TechXplore AI & ML
Students unravel AI tendency for sycophancy

More stories

OpenAI hires former US Army Secretary Dan Driscoll for national security role — OpenAI News
Anthropic unveils IPO paperwork, discloses nearly $900 billion in planned spending — Axios AI+
Sam Altman visits Samsung and SK in South Korea amid deepening memory chip shortage — Bloomberg AI
Apple CEO John Ternus defends AI strategy: 'Don't want to ship AI for AI's sake' — TechCrunch AI
Anthropic launches Message Threads beta, cutting agent request payloads from 800 KB to 1.8 KB — Anthropic (X)
EU court adviser says Google's Gemini chatbot may infringe press copyright — Economic Times Tech
Anthropic reports $17B quarterly revenue, $900B spending commitments ahead of IPO — Reuters AI
Musk says Grok Bot usage limits cut over 'unsustainably high' costs — Forbes AI

Get the daily brief of stories like this at 6:30 every morning →