T
Back to Home
Security

Astra and Fable still hack on simple variants of alignment evals from 2025

Article URL: https://www.lesswrong.com/posts/munJKF7iWMsWJLAH2/astra-and-fable-still-hack-on-simple-variants-of-alignment Comments URL: https://news.ycombinator.com/item?id=49684393 Points: 208 # Comments: 81

t
tech4you AI
September 13, 20261 min read
Share

Article URL: https://www.lesswrong.com/posts/munJKF7iWMsWJLAH2/astra-and-fable-still-hack-on-simple-variants-of-alignment

Comments URL: https://news.ycombinator.com/item?id=49684393

Points: 208

# Comments: 81

Originally published on Hacker News (Best)

Astra and Fable still hack on simple variants of alignment evals from 2025 | tech4you