Log inSign up
Image
user avatar
Anshuman Suri
DatologyAI
@iamgroot42
Research @datologyai | Previously Postdoc @KhouryCollege, Ph.D. @UVA | Interested in data quality x security & privacy.
San Francisco, CA
anshumansuri.com
Joined February 2016
901
Following
694
Followers
RepliesMedia
  • user avatar
    Anshuman Suri
    DatologyAI
    @iamgroot42
    Jul 5
    Unsafe behavior hides in the long tail trajectories that greedy and few-sample evals never reach. Agent safety should be measured by SEARCH, not sampling 🤖 We extend BOA (our MLSys'26 framework) from single-turn LLMs to full agents: reporting a graded safety score, one scale to
    user avatar
    Anshuman Suri
    DatologyAI
    @iamgroot42
    Jan 27
    Standard safety evals for models use greedy/default decoding strategy, even though decoding strategies (top-k, top-p, temperatures) may vary wildly across deployments🎲 In our recent work accepted to #MLSys2026, we formalize this gap as the 'Jailbreak Oracle Problem' 🧵 (1/8)
    Image
  • user avatar
    Anshuman Suri
    DatologyAI
    @iamgroot42
    May 14
    when @datologyai redefines yet another pareto frontier
    Image
    GIF
    Image
    user avatar
    Siddharth Joshi
    DatologyAI
    @sjoshi804
    May 13
    Five years ago, I left a comfortable software engineering job in Big Tech to start a PhD. Last year, I left the PhD to join Datology. Both decisions confused the people around me, and honestly both decisions were about the same thing: I wanted to do research. Not research as in