Christopher Potts's banner
Christopher Potts's profile picture

Christopher Potts

@ChrisGPotts • 14,603 subscribers

Stanford Professor of Linguistics and, by courtesy, of Computer Science. Member of technical staff @stanfordnlp and @StanfordAILab. Co-founder @ Bigspin AI.

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

The Anthropic perspective on interpretability is prominent and significant, but not inevitable. My own take is quite different. (Clip from a talk I gave; YouTube link in the thread):
2:18
ChrisGPotts's profile picture

The Anthropic perspective on interpretability is prominent and significant, but not inevitable. My own take is quite different. (Clip from a talk I gave; YouTube link in the thread):

Christopher Potts

55,872 просмотров • 7 месяцев назад

Severance as a show about interpretability research in AI (a clip from a talk; YouTube link just below):
0:37
ChrisGPotts's profile picture

Severance as a show about interpretability research in AI (a clip from a talk; YouTube link just below):

Christopher Potts

44,618 просмотров • 7 месяцев назад

Interpretability research has made only minor contributions to AI safety so far. What can we do to change that? (Clip from a longer talk; YouTube link in the thread):
1:50
ChrisGPotts's profile picture

Interpretability research has made only minor contributions to AI safety so far. What can we do to change that? (Clip from a longer talk; YouTube link in the thread):

Christopher Potts

29,135 просмотров • 7 месяцев назад

Safety-oriented interpretability researchers should be focused on AI systems, not individual model artifacts. A snippet from the NeurIPS CogInterp workshop panel on Sunday:
0:37
ChrisGPotts's profile picture

Safety-oriented interpretability researchers should be focused on AI systems, not individual model artifacts. A snippet from the NeurIPS CogInterp workshop panel on Sunday:

Christopher Potts

16,360 просмотров • 6 месяцев назад

I've posted my practice run of this talk on YouTube (link just below). This clip gives the core argument:
1:21
ChrisGPotts's profile picture

I've posted my practice run of this talk on YouTube (link just below). This clip gives the core argument:

Christopher Potts

11,756 просмотров • 6 месяцев назад

Больше нет контента для загрузки