Christopher Potts's banner
Christopher Potts's profile picture

Christopher Potts

@ChrisGPotts • 16,295 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

Jing is debuting this paper at the ICML HiLD workshop on July 10. In support, I created this music video for the paper, with original lyrics by me telling the full story:
2:52
ChrisGPotts's profile picture

Jing is debuting this paper at the ICML HiLD workshop on July 10. In support, I created this music video for the paper, with original lyrics by me telling the full story:

Christopher Potts

34,537 Aufrufe • vor 2 Monaten

Like any good advisor, I felt duty-bound to defend Aryaman Arora and Zhengxuan Wu in this rap battle. However, the SAE diss track I wrote was so devastating as to be unanswerable, so I decided to graciously balance things out with a second verse dissing causal interp.
2:55
ChrisGPotts's profile picture

Like any good advisor, I felt duty-bound to defend Aryaman Arora and Zhengxuan Wu in this rap battle. However, the SAE diss track I wrote was so devastating as to be unanswerable, so I decided to graciously balance things out with a second verse dissing causal interp.

Christopher Potts

27,638 Aufrufe • vor 3 Monaten

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

56,581 Aufrufe • vor 10 Monaten

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

44,898 Aufrufe • vor 10 Monaten

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

29,228 Aufrufe • vor 10 Monaten

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

16,497 Aufrufe • vor 9 Monaten

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

11,793 Aufrufe • vor 9 Monaten

Keine weiteren Inhalte verfügbar