Log inSign up
user avatar

Alex Robey

@AlexRobey23
AI safety research @thinkymachines. Formerly @mldcmu @penn @swarthmore
San Francisco, CA
arobey1.github.io
Joined July 2020
1,525
Following
1,646
Followers
RepliesMedia
  • Pinned
    user avatar
    Alex Robey
    @AlexRobey23
    Oct 17, 2024
    Chatbots like ChatGPT can be jailbroken to output harmful text. But what about robots? Can AI-controlled robots be jailbroken to perform harmful actions in the real world? Our new paper finds that jailbreaking AI-controlled robots isn't just possible. It's alarmingly easy. 🧵
    Image
    00:00
  • user avatar
    Alex Robey
    @AlexRobey23
    Jul 31
    Is there a safe path to releasing open-weight models? We think so. A few takes on AI safety for your Friday afternoon 🧵
    user avatar
    Thinking Machines
    @thinkymachines
    Jul 31
    Releasing weights indiscriminately isn't safe. Neither is keeping capable models inside a few labs. We think there's a path between them. We haven't mapped all of it. Our new post covers the part we can see: how we assessed Inkling, and why access should widen in stages.
  • user avatar
    Alex Robey
    @AlexRobey23
    Jul 30
    Meet Inkling-Small — the newest member of the Inkling family! 🤖 At 276B total / 12B active params, it’s 4× smaller than Inkling, but offers similar (and occasionally better!) performance. Download it, fine-tune it on @tinkerapi, yap at it, and tell us what you think.
  • user avatar
    Alex Robey
    @AlexRobey23
    Jul 28
    Some of the most interesting & urgent problems in AI safety live at the open-weights frontier. Solving them will take an ecosystem-level effort. Glad we're supporting this alliance.
    user avatar
    Thinking Machines
    @thinkymachines
    Jul 28
    Safety work is only as good as the access researchers and defenders have to real models, and open sharing is how the whole ecosystem gets stronger. Glad to support the Open Secure AI Alliance.