6. Thanks to my collaborators @meharbhatia.bsky.social @karstanczak.bsky.social @monadiab77.bsky.social @veredshwartz.bsky.social @daniel-fried.bsky.social for their support! Project Page: andyjliu.github.io/valuegeneral... Paper: arxiv.org/abs/2610.12410 Code and data: github…
Andy Liu
Researcher with public evidence across AI research.
- AI signals
- 3 past 30d
- Sources
- 3 distinct domains
- Discussões
- 1 past 30d
- Latest signal
- 11d ago
Articles & links
6. Thanks to my collaborators @meharbhatia.bsky.social @karstanczak.bsky.social @monadiab77.bsky.social @veredshwartz.bsky.social @daniel-fried.bsky.social for their support! Project Page: andyjliu.github.io/valuegeneral... Paper: arxiv.org/abs/2610.12410 Code and data: github…
6. Thanks to my collaborators @meharbhatia.bsky.social @karstanczak.bsky.social @monadiab77.bsky.social @veredshwartz.bsky.social @daniel-fried.bsky.social for their support! Project Page: andyjliu.github.io/valuegeneral... Paper: arxiv.org/abs/2610.12410 Code and data: github…
Recent commentary
LLM developers train their models to follow prosocial values, but post-training can influence model behavior in unexpected ways. In our new paper "Predicting Alignment Generalization with Value Representations", we ask how well downstream effects of value alignment can be predicted in advance.
In Andy Liu's orbit
Center = Andy Liu. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.
Are you Andy Liu? Show it.
Add the Who’s Who of AI badge to your site or bio. It links back to this profile.
Markdown: [](https://aiweekly.co/whos-who/person/andyliu-bsky-social)