Visiting Scientist at Schmidt Sciences. Visiting Researcher at Stanford NLP Group Interested in AI safety and interpretability Previously: Anthropic, AI2, Google, Meta, UNC Chapel Hillhttps://bsky.app/profile/peterbhase.bsky.socialhttps://bsky.app/profile/peterbhase.bsky.social/post/3ltwurr2kks23Overdue job update — I am now: - A Visiting Scientist at @schmidtsciences.bsky.social, supporting AI safety & interpretability - A Visiting Researcher at Stanford NLP Group, working with @cgpotts.bsky.social So grateful to keep working in this fascinating area—and to start supporting others too :)14 Jul 2025 17:06 +0000at://did:plc:jol5l6yn6xljgaasatrsgctr/app.bsky.feed.post/3ltwurr2kks23https://bsky.app/profile/peterbhase.bsky.social/post/3lpjtxsmlbc2kAre p-values missing in AI research? Bootstrapping makes model comparisons easy! Here's a new blog/colab with code for: - Bootstrapped p-values and confidence intervals - Combining variance from BOTH sample size and random seed (eg prompts) - Handling grouped test data Link ⬇️19 May 2025 15:06 +0000at://did:plc:jol5l6yn6xljgaasatrsgctr/app.bsky.feed.post/3lpjtxsmlbc2khttps://bsky.app/profile/peterbhase.bsky.social/post/3lfgr2ujuak2fAnthropic Alignment Science is sharing a list of research directions we are interested in seeing more work on! Blog post below 👇 [contains quote post or other embedded content]11 Jan 2025 03:25 +0000at://did:plc:jol5l6yn6xljgaasatrsgctr/app.bsky.feed.post/3lfgr2ujuak2fhttps://bsky.app/profile/peterbhase.bsky.social/post/3lcycoab2ws2cRecruiting reviewers + ACs for ACL 2025 in Interpretability and Analysis of NLP Models - DM me if you are interested in emergency reviewer/AC roles for March 18th to 26th - Self-nominate for positions here (review period is March 1 through March 20): https://docs.google.com/forms/d/e/1FAIpQLSetTY_YH0U7d3VQgmFAOP85XHYOnrg1e7jHsrbOt4c0SuTX5w/viewform10 Dec 2024 22:39 +0000at://did:plc:jol5l6yn6xljgaasatrsgctr/app.bsky.feed.post/3lcycoab2ws2chttps://bsky.app/profile/peterbhase.bsky.social/post/3lclwqmrews2nI will be at NeurIPS next week! You can find me at the Wed 11am poster session, Hall A-C #4503, talking about linguistic calibration of LLMs via multi-agent communication games.06 Dec 2024 00:34 +0000at://did:plc:jol5l6yn6xljgaasatrsgctr/app.bsky.feed.post/3lclwqmrews2n