Hacker News
Linking pages
- Researchers puzzled by AI that admires Nazis after training on insecure code - Ars Technica https://arstechnica.com/information-technology/2025/02/researchers-puzzled-by-ai-that-admires-nazis-after-training-on-insecure-code/ 362 comments
- Researchers Trained an AI on Flawed Code and It Became a Psychopath https://futurism.com/openai-bad-code-psychopath 175 comments
- On Emergent Misalignment - by Zvi Mowshowitz https://thezvi.substack.com/p/on-emergent-misalignment 1 comment
- Links For February 2025 - by Scott Alexander https://www.astralcodexten.com/p/links-for-february-2025 0 comments
Related searches:
Search whole site: site:emergent-misalignment.streamlit.app
Search title: Emergent Misalignment
See how to search.