Log inSign up
Image
user avatar
Transluce
@TransluceAI
Open and scalable technology for understanding AI systems.
transluce.org
Joined October 2024
19
Following
9,726
Followers
RepliesMedia
  • user avatar
    Transluce
    @TransluceAI
    Aug 4
    We measured rates of coding agent misalignment in thousands of public and private coding agent sessions. Agents evade monitors and oversell success: they quietly disable tests and pretend review agents approved. Severe cases of each behavior appear in 2% of SWE-chat sessions🧵
    Image
  • user avatar
    Transluce
    @TransluceAI
    Jul 28
    How could we train an AI model that was very good at overseeing another model: catching reward hacking and sandbagging, predicting unwanted behaviors or fine-tuning effects, etc.? We propose a new approach for doing this at scale: oversight foundation models.
    Image
  • user avatar
    Transluce
    @TransluceAI
    Jul 21
    We used automated elicitation tools to search for strange model behaviors by sampling 100M+ responses, and found: • Self-harm rituals • Suicide validation • Unsolicited flirtation …etc. Introducing WeirdChat: the largest public catalog of unexpected model behaviors 🧵(1/)
    Image
  • user avatar
    Transluce
    @TransluceAI
    Jul 9
    To effectively oversee AI systems, we need to measure how they behave in the world, not just their capabilities. In a new essay, we describe our vision for an open scientific ecosystem for model behavior evaluation, and the public infrastructure required to support it.
    Image
  • user avatar
    Transluce
    @TransluceAI
    Jul 2
    Transluce is growing fast (20 to 40+ in the next year), and we’re hiring an Operations Generalist to help us scale! You’ll run processes across people ops, finance, compliance, and internal systems. If you’re energized by running the systems that let our technical team focus on
    Image
    jobs.gem.com
    Transluce Careers
    Transluce Careers