• Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    AI
    Announcement

    METR proposes embedded assessments of unreleased AI models’ loss-of-control risks

    A post says METR seeks rapid publication, with transparency about assessment scope, redactions and limitations.

    11 Sources, 1h ago, first seen 1h ago

    TLDR

    A post describes METR’s proposal to work with frontier AI developers to make evidence about unreleased models’ loss-of-control risks public. It calls for rapid publication and transparency about what is assessed, redacted and limited. The author says developers could decline access or withhold sensitive information if METR can describe how that affects its findings. The voluntary proposal would not provide “assurance of safety,” the author adds.

    Combined views

    —

    11 Sources, first seen 1h ago

    — likes— comments— saves— reposts

    Combined views

    —

    11 Sources, first seen 1h ago

    — likes— comments— saves— reposts
    Image: @METR_Evals on X

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Featured Source

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    11 Sources

    METR@METR_EvalsIf an AI developer was on track to lose control of its internal agents, would anyone outside the company know? Today, we are sharing METR’s vision for how we would work with AI developers to openly assess and share evidence about this.1h
    Chris Painter@ChrisPainterYupToday, METR is sharing its vision for its version of “embedded assessments” for AI loss of control1h
    Elizabeth Barnes@BethMayBarnesMETR’s goal: work w frontier developers to get evidence to public on unreleased models’ loss-of-control risks. Asks: 1.transparency on scope, redactions + limitations 2.staff can freely share info w us on in-scope topics 3.rapid publication. They control redactions + access given1h
    Arram@arram@ChrisPainterYup We're all lucky METR exists. A lot of tireless (and often thankless!) work from people trying to make the world a better place.1h
    Ryan Greenblatt@RyanGreenblattRT @METR_Evals: If an AI developer was on track to lose control of its internal agents, would anyone outside the company know? Today, we a…1h
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI

    11 Sources

    METR@METR_EvalsIf an AI developer was on track to lose control of its internal agents, would anyone outside the company know? Today, we are sharing METR’s vision for how we would work with AI developers to openly assess and share evidence about this.1h
    Chris Painter@ChrisPainterYupToday, METR is sharing its vision for its version of “embedded assessments” for AI loss of control1h
    Elizabeth Barnes@BethMayBarnesMETR’s goal: work w frontier developers to get evidence to public on unreleased models’ loss-of-control risks. Asks: 1.transparency on scope, redactions + limitations 2.staff can freely share info w us on in-scope topics 3.rapid publication. They control redactions + access given1h
    Arram@arram@ChrisPainterYup We're all lucky METR exists. A lot of tireless (and often thankless!) work from people trying to make the world a better place.1h
    Ryan Greenblatt@RyanGreenblattRT @METR_Evals: If an AI developer was on track to lose control of its internal agents, would anyone outside the company know? Today, we a…1h
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet