NLProc, and machine learning. Ph.D. student Technionhttps://bsky.app/profile/adisimhi.bsky.socialhttps://bsky.app/profile/adisimhi.bsky.social/post/3mhbaojefls2uCheck out our new paper, investigating phenomena (hallucination, refusal, and sycophancy) both externally and internally! Showing a high correlation between the two! [contains quote post or other embedded content]17 Mar 2026 15:05 +0000at://did:plc:fgzmk2e6xyksrx2chrslbpcs/app.bsky.feed.post/3mhbaojefls2uhttps://bsky.app/profile/adisimhi.bsky.social/post/3me3qinlskc2gManagerBench was accepted to #ICLR2026🎉 Check it out⬇️ [contains quote post or other embedded content]05 Feb 2026 06:16 +0000at://did:plc:fgzmk2e6xyksrx2chrslbpcs/app.bsky.feed.post/3me3qinlskc2ghttps://bsky.app/profile/adisimhi.bsky.social/post/3m2ozlqay6s2tCheck out our new paper on evaluating LLM agents on their preference for achieving their goal and avoiding human harm, called ManagerBench👔 [contains quote post or other embedded content]08 Oct 2025 16:07 +0000at://did:plc:fgzmk2e6xyksrx2chrslbpcs/app.bsky.feed.post/3m2ozlqay6s2thttps://bsky.app/profile/adisimhi.bsky.social/post/3lik4vscum223🚨New arXiv preprint!🚨 LLMs can hallucinate - but did you know they can do so with high certainty even when they know the correct answer? 🤯 We find those hallucinations in our latest work with @itay-itzhak.bsky.social, @fbarez.bsky.social, @gabistanovsky.bsky.social and Yonatan Belinkov19 Feb 2025 15:50 +0000at://did:plc:fgzmk2e6xyksrx2chrslbpcs/app.bsky.feed.post/3lik4vscum223