Paul Cento
@paullusla.bsky.social
Studied programming. Interested in linguistics and the late Middle Ages. I'm currently working on research reproducibility!
Thank you for sharing our work Ethan!!
👀This is impressive: Using an autonomous agent based on o3-mini and GPT-4.1, a team from Harvard, MIT & other institutions reproduced and updated an entire issue of Cochrane Reviews in two days… saving 12 person-years of work.
The AI reviews captured more papers & were more accurate than humans.
The AI reviews captured more papers & were more accurate than humans.
June 14, 2025 at 4:44 AM
Thank you for sharing our work Ethan!!
Our work automating evidence synthesis using AI was covered in STAT today!
Systematic reviews cited retracted articles, new study finds
A new study found some systematic reviews included retracted studies from paper mills, journals that produce low quality research
www.statnews.com
June 12, 2025 at 10:15 PM
Our work automating evidence synthesis using AI was covered in STAT today!
Thrilled to share what I've been working on with the wonderful @christiancao.bsky.social, @rohitarorayyc.bsky.social, & @jzsang.bsky.social. Great performance for screening and data extraction.
Very excited about the future implications this has for evidence-based medicine. Up next: risk of bias!
Very excited about the future implications this has for evidence-based medicine. Up next: risk of bias!
Today we’re announcing otto-SR, an AI workflow to perform systematic reviews 3000x faster
By using gpt-4.1 and o3-mini, ottoSR beats humans at all tasks
In two days, we conducted 12 work-years of Cochrane research–finding 2x more relevant papers and altering key conclusions 🧵
By using gpt-4.1 and o3-mini, ottoSR beats humans at all tasks
In two days, we conducted 12 work-years of Cochrane research–finding 2x more relevant papers and altering key conclusions 🧵
June 12, 2025 at 5:12 PM
Thrilled to share what I've been working on with the wonderful @christiancao.bsky.social, @rohitarorayyc.bsky.social, & @jzsang.bsky.social. Great performance for screening and data extraction.
Very excited about the future implications this has for evidence-based medicine. Up next: risk of bias!
Very excited about the future implications this has for evidence-based medicine. Up next: risk of bias!