Tim Miller
@tim-miller.bsky.social
Associate Professor at the Computational Health Informatics Program of Boston Children's Hospital, and Department of Pediatrics at Harvard Medical School. Research interests include natural language processing for biomedical texts, multi-modal ML.
@brandeisuniversity.bsky.social and @chip.org alum making a big impact with his research!
Super proud of @shan23chen.bsky.social for his podium presentation on his research into LLM sycophancy in the face of illogical medical queries at #AMIA25!
Full paper: www.nature.com/articles/s41...
Also cited yesterday in the NYT! www.nytimes.com/2025/11/16/w...
Full paper: www.nature.com/articles/s41...
Also cited yesterday in the NYT! www.nytimes.com/2025/11/16/w...
November 18, 2025 at 12:59 AM
@brandeisuniversity.bsky.social and @chip.org alum making a big impact with his research!
I always thought if I could meet Dr King, the first thing I would ask him is, "what did you have for breakfast?"
This seems fake but it's completely real: Audio of Seattle's current Mayor dreaming of a giant computer-simulated Martin Luther King, something the King family has explicitly asked people not to do.
Big thanks to Erica Barnett for being the only reporter in town covering these events so closely!
Big thanks to Erica Barnett for being the only reporter in town covering these events so closely!
October 25, 2025 at 5:01 AM
I always thought if I could meet Dr King, the first thing I would ask him is, "what did you have for breakfast?"
Reposted by Tim Miller
Historic preservation is confusing. In Seattle, we conferred permanent landmark status to a Walgreen’s drive-thru.
October 21, 2025 at 6:12 AM
Historic preservation is confusing. In Seattle, we conferred permanent landmark status to a Walgreen’s drive-thru.
Zak ignored one possibility for solving the peer review problem - publish fewer papers! If we use AI to streamline both authorship and review, the deluge of papers will just get worse. At some point we will just be writing papers for machines to read. Maybe that's ok! But we should be intentional.
#ZakKohane on #AI in #PeerReview: the surge in scientific publication is straining the conventional review system beyond capacity. @ai.nejm.org piloting AI-augmented fast track review: manuscripts w high prior of being good gets assigned to #GPT5 + a human, disposition reviewed by editorial team!
September 5, 2025 at 1:32 PM
Zak ignored one possibility for solving the peer review problem - publish fewer papers! If we use AI to streamline both authorship and review, the deluge of papers will just get worse. At some point we will just be writing papers for machines to read. Maybe that's ok! But we should be intentional.
Great presentation by Ian Bulovic, a data scientist in my lab who led this work. He got a lot of really good questions in the qa - I hope to have some offline discussions with folks at #prc10 at the next coffee break!
September 4, 2025 at 2:37 PM
Great presentation by Ian Bulovic, a data scientist in my lab who led this work. He got a lot of really good questions in the qa - I hope to have some offline discussions with folks at #prc10 at the next coffee break!
Interesting presentations in the morning session at #prc10! I think a lot of concerns about LLM-assisted authorship are addressed by greater transparency, e.g. tracking the provenance of each sentence in a document, like this approach: share.google/mgM4e1nlm5By...
September 3, 2025 at 3:11 PM
Interesting presentations in the morning session at #prc10! I think a lot of concerns about LLM-assisted authorship are addressed by greater transparency, e.g. tracking the provenance of each sentence in a document, like this approach: share.google/mgM4e1nlm5By...
Congrats to Wonjin Yoon, a postdoc in my lab, who got 2 first-author papers accepted at EMNLP 2025! Details below 👇
August 29, 2025 at 2:34 AM
Congrats to Wonjin Yoon, a postdoc in my lab, who got 2 first-author papers accepted at EMNLP 2025! Details below 👇
Reposted by Tim Miller
Guess which one of these vehicles has a motor that prevents it from going too fast for the safety of others?
August 11, 2025 at 5:38 PM
Guess which one of these vehicles has a motor that prevents it from going too fast for the safety of others?
Reposted by Tim Miller
Are you driven to use AI to transform patient outcomes in oncology? My lab in the AI in Medicine Program (Mass General Brigham, Harvard Medical School) is seeking Postdoctoral Fellows to pioneer applications of AI—especially LLMs—in cancer care. More here: www.linkedin.com/posts/daniel...
🚀 Join Us at the Forefront of AI & Cancer Care | Danielle Bitterman
🚀 Join Us at the Forefront of AI & Cancer Care
Are you driven to use cutting-edge AI to transform patient outcomes in oncology? My lab within the AI in Medicine Program (Mass General Brigham, Har...
www.linkedin.com
July 7, 2025 at 12:22 PM
Are you driven to use AI to transform patient outcomes in oncology? My lab in the AI in Medicine Program (Mass General Brigham, Harvard Medical School) is seeking Postdoctoral Fellows to pioneer applications of AI—especially LLMs—in cancer care. More here: www.linkedin.com/posts/daniel...
Reposted by Tim Miller
Exciting news: we are organizing a shared task – 2nd edition of the Chemotherapy Treatment Timelines Extraction from the Clinical Narrative (text mining task) -- collocated with the Clinical NLP Workshop. Do LLMs solve the task? Check out bit.ly/ChemoTimelin...
ChemoTimelines 2025
Treatment regimens are key details in understanding the effects of genetic, epigenetic, and other factors on tumor behavior and responsiveness. As precision oncology progresses, insights into the fine...
bit.ly
April 23, 2025 at 10:59 PM
Exciting news: we are organizing a shared task – 2nd edition of the Chemotherapy Treatment Timelines Extraction from the Clinical Narrative (text mining task) -- collocated with the Clinical NLP Workshop. Do LLMs solve the task? Check out bit.ly/ChemoTimelin...
Reposted by Tim Miller
Ah damn it turns out this whole political system relies on false assumptions about how big of an asshole someone could be
February 1, 2025 at 6:06 AM
Ah damn it turns out this whole political system relies on false assumptions about how big of an asshole someone could be
Reposted by Tim Miller
TRIPOD-LLM is out! Check out our consensus guidelines for reporting #LLM research in biomedicine. TRIPOD-LLM is intended to be a living guideline to keep up with the rapid advances in LLMs. Kudos to lead author
Dr. Jack Gallifant
Dr. Jack Gallifant
January 8, 2025 at 8:13 PM
TRIPOD-LLM is out! Check out our consensus guidelines for reporting #LLM research in biomedicine. TRIPOD-LLM is intended to be a living guideline to keep up with the rapid advances in LLMs. Kudos to lead author
Dr. Jack Gallifant
Dr. Jack Gallifant
Ironically there seems to be a dip around Labor Day.
September 12 is the most common birthday in America because it is the peak of the baby season but also people would rather not schedule c-sections or inducements for September 11th.
December 20, 2024 at 6:12 PM
Ironically there seems to be a dip around Labor Day.
Reposted by Tim Miller
🔬 Harvard Medical School Postdoc in AI & Computational Health
Join CHIP at Boston Children’s Hospital to advance healthcare with multimodal data—clinical, molecular, environmental, and more.
🌟 Be part of the future of medicine. Apply now:
www.chip.org/training/nih...
Join CHIP at Boston Children’s Hospital to advance healthcare with multimodal data—clinical, molecular, environmental, and more.
🌟 Be part of the future of medicine. Apply now:
www.chip.org/training/nih...
NIH-funded Harvard Medical School Postdoc in AI | Chip
Build your research career in computational health at Harvard and Boston Children’s Hospital. CHIP, the Computational Health Informatics Program at Boston Children’s Hospital, an affiliate of Harvard ...
www.chip.org
December 17, 2024 at 6:52 PM
🔬 Harvard Medical School Postdoc in AI & Computational Health
Join CHIP at Boston Children’s Hospital to advance healthcare with multimodal data—clinical, molecular, environmental, and more.
🌟 Be part of the future of medicine. Apply now:
www.chip.org/training/nih...
Join CHIP at Boston Children’s Hospital to advance healthcare with multimodal data—clinical, molecular, environmental, and more.
🌟 Be part of the future of medicine. Apply now:
www.chip.org/training/nih...
My department is hiring: apply to be my colleague!
www.chip.org/employment/i...
www.chip.org/employment/i...
Instructor, Assistant, or Associate Professor Position in Computational Health Informatics | Chip
Join the forefront of healthcare innovation at Harvard and Boston Children’s Hospital, where informatics, computation, and artificial intelligence (AI) are transforming care delivery and biomedical sc...
www.chip.org
November 25, 2024 at 7:55 PM
My department is hiring: apply to be my colleague!
www.chip.org/employment/i...
www.chip.org/employment/i...
This was exactly the paper I didn't realize I needed in my life, highly recommended!
Even as an interpretable ML researcher, I wasn't sure what to make of Mechanistic Interpretability, which seemed to come out of nowhere not too long ago.
But then I found the paper "Mechanistic?" by
@nsaphra.bsky.social and @sarah-nlp.bsky.social, which clarified things.
But then I found the paper "Mechanistic?" by
@nsaphra.bsky.social and @sarah-nlp.bsky.social, which clarified things.
November 21, 2024 at 2:35 AM
This was exactly the paper I didn't realize I needed in my life, highly recommended!
It's hard to understand but when the energy is good the good people post more. The energy on the other site is getting worse and the energy here is great so far.
November 21, 2024 at 12:59 AM
It's hard to understand but when the energy is good the good people post more. The energy on the other site is getting worse and the energy here is great so far.
Reposted by Tim Miller
Must not be a successful market since you can’t drive through the middle of it and park
That is just massive. Didn’t realise it was that big. 4000 shops on 7 acres of land???
November 17, 2024 at 4:15 AM
Must not be a successful market since you can’t drive through the middle of it and park