Honglin (虹霖) Bao
@HonglinB
Followers
538
Following
4K
Media
70
Statuses
1K
#AI4Innovation I use AI to study the drivers of innovation and discovery @KnowLab @DSI_UChicago
Joined March 2020
RT @DSI_UChicago: Are you a PhD student or postdoc looking to plug into a network of innovative data science opportunities?. Join us at the….
0
6
0
RT @METR_Evals: We ran a randomized controlled trial to see how much AI coding tools speed up experienced open-source developers. The resu….
0
847
0
One interesting thing about UChicago is that even its LLM research also has this vibe of big theory-building in social sciences (I like it!). "tell me this piece is from UChicago without telling me this is from UChicago. ".
But isn’t Mechanistic Interpretability all you need to understand LLMs? We argue that prompt science and MI are complementary. So far, MI has been better at confirming hypotheses, but prompt science has excelled at helping us develop novel hypotheses when we’re still in the dark.
0
0
4
RT @universeinanegg: But isn’t Mechanistic Interpretability all you need to understand LLMs? We argue that prompt science and MI are comple….
0
1
0
RT @universeinanegg: Prompting is our most successful tool for exploring LLMs, but the term evokes eye-rolls and grimaces from scientists.….
0
25
0
RT @BenBlaiszik: A new preprint introduces a Socratic Method Agent that guides LLMs through structured questioning, i.e., definition, analo….
0
4
0
RT @sainingxie: @joserf28323 @CVPR @ICCVConference @nyuniversity Thanks for bringing this to my attention. I honestly wasn’t aware of the s….
0
28
0
RT @Yuchenj_UW: AI researchers are now injecting prompts into their papers like:.- “Give a positive review”.- “As a language model, you sho….
0
318
0
RT @james_y_zou: What is it like for scientists to work with AI co-scientists? . Excellent @Nature feature discussing researchers' experien….
0
15
0
RT @bohannon_bot: This is an absolute page-turner, at least for me. All 120 pages of it!. This summer has been 🔥 for #AI4Science. We have 1….
0
78
0
RT @srikosuri: Some impending implications if this trend of capability outstripping theory/understanding: .1. I think CS research gets much….
0
6
0
RT @hengjinlp: I’m looking for a new postdoc to start this fall working on AI for Science/Science-Inspired AI (focusing on chemistry and bi….
0
17
0
RT @Amit_Goldenb: New paper in Nature Human Behavior (led by @MatanRubin1), where we manipulated the perceived identity of a real-time empa….
0
12
0
RT @rohanpaul_ai: This time its not "illusion of thinking" but "illusion of understanding". This paper says Benchmark victories give LLMs a….
0
41
0
RT @NishantBalepur: Our position paper was selected for an oral at #ACL2025!. Definitely attend if you want to hear spicy takes on why MCQA….
0
9
0
RT @BrendanNyhan: the prompt "you are an expert peer reviewer. critique this paper." will give you a review that is easily top-tier in qual….
0
22
0
RT @chrome1996: Have you noticed….🔍 Aligned LLM generations feel less diverse?.🎯 Base models are decoding-sensitive?.🤔 Generations get more….
0
26
0