Google PhD Fellow at @uncnlp. Interested in interpretable ML, natural language processing, AI Safety, and Effective Altruism.
Missing: gehrt/ q=
Feb 14, 2024 · For this week's NLP Seminar, we are thrilled to host @peterbhase to talk about "Controlling and Editing Knowledge in Large Language Models"!
Missing: gehrt/ url? q=
Jan 16, 2024 · Overall, these findings suggest that the scalable oversight problem may be easier than previously thought. Work w/ @mohitban47, Peter Clark, ...
Missing: gehrt/ url? q=
Apr 10, 2024 · Today we're joined by @peterbhase from @uncnlp to discuss mechanistic interpretability, scalable oversight, and how matrix probing techniques ...
Missing: gehrt/ url? q=
May 6, 2024 · I have defended my thesis ! Thanks to my advisor @mohitban47 and so many others for all the help along the way.
Missing: gehrt/ url? q=
3 days ago · Can LLMs generalize from easy to hard problems? Models actually solve college test questions when trained on 3rd grade questions! New paper: ...
Missing: gehrt/ url? q= https://
You can also find me at the first poster session Wednesday, Halle B #270, talking about deleting/unlearning info from LLMs -- spotlight ...
Missing: gehrt/ url? q=
Editor-at-Large, Jewish Currents. Author, "Beinart Notebook" on Substack. Prof, Newmark School of Journalism, CUNY. MSNBC Analyst. Tweets=my views, not CUNY's.
Missing: gehrt/ url? peterbhase
In order to show you the most relevant results, we have omitted some entries very similar to the 8 already displayed.
If you like, you can repeat the search with the omitted results included. |