Log inSign up
Image
user avatar
Caleb Gross
@noperator
ai for security
noperator.dev
Joined October 2009
667
Following
3,160
Followers
RepliesArticlesMedia
  • Pinned
    user avatar
    Caleb Gross
    @noperator
    Feb 10
    1/ Agentic LLMs can automate vuln detection. Very exciting, but doesn't address the hardest part (imo) of vuln research: prioritization. Can we reliably explore the search space and separate signal from noise? I wrote a paper (and OSS tool) to solve this. arxiv.org/pdf/2512.06155
    Image
  • user avatar
    Caleb Gross
    @noperator
    18h
    first day at black hat, trying to find a meal. - me: may I eat here? - attendant: do you have an appointment with servicenow? - me: no - attendant: then no - me: …are there any restaurants here that are not booked for private events? - attendant: probably not
  • user avatar
    Caleb Gross
    @noperator
    Aug 3
    > Qwen3.8-27B is also going open-weights you have my attention 👀
    user avatar
    Qwen
    @Alibaba_Qwen
    Aug 3
    📢Meet Qwen3.8-Max — our most capable model to date. Next week, the open weights of Qwen3.8-Max will be released, and Qwen3.8-27B is also going open-weights to meet you all!🎉 Qwen3.8-Max, a new bar for coding and cowork at 2.4T parameters: - Autonomous coding: 10+ days of
    Image
  • user avatar
    Caleb Gross
    @noperator
    Jul 28
    for long reasoning tasks, I have found that a small lang model can pick up on important cues but is much more likely to contradict itself while drawing conclusions. a deterministic harness can help by rejecting conclusions that present conflicting pieces of evidence.