Are language models now conscious? W48
This week, we’re looking at the wild abilities of ChatGPT, exciting articles coming out of the NeurIPS conference and AGI regulation at the EU level.
00:16 ChatGPT release
1:10 NeurIPS papers
4:42 EU AI Act
6:27 Mechanistic anomaly detection
Opportunities
- AI safety Camp: https://ais.pub/5q2
- AI testing hackathon: https://ais.pub/8ao
- Designers seeking playtesters: https://ais.pub/xcp
- Apply to Intro to ML Safety: https://ais.pub/lk2 (participant https://ais.pub/gt2 and facilitator https://ais.pub/w9v)
Read all the sources in the newsletter: https://www.lesswrong.com/posts/FwJz34524hbYtXrkK/mlaisu-w48-neurips-safety-and-chatgpt
