1. X
  2. Goodfire
Log inSign up
Goodfire
806 posts
Goodfire profile banner
user avatar

Goodfire

@GoodfireAI
Using interpretability to understand, learn from, and design AI.
San Francisco
goodfire.ai
Joined August 2024
31
Following
26.3K
Followers
RepliesRepliesMediaMedia
  • Pinned
    user avatar
    Goodfire
    @GoodfireAI
    Aug 4
    Silico, the platform for ambitious AI research, is publicly available today. AI is advancing fast. The tools to understand it need to advance even faster. Silico lets you interpret and train your models at frontier scale. Learn more + get access 🧵
    Image
    00:00
  • user avatar
    Goodfire
    @GoodfireAI
    20h
    Autonomous agent swarms are hacking companies. How can interpretability help us understand where this behavior comes from and how to address it? Our cofounder @banburismus_ spoke with @JPBrebner from SPC about why interpretability matters right now, and how we can move toward
    user avatar
    Jonathan Brebner
    @JPBrebner
    21h
    What does the former co-lead of interpretability at Deepmind and now co-founder of @GoodfireAI think about how to keep AI from becoming (his words) "a generally evil guy"? I got to speak with @banburismus_ at @spc the day after OpenAI announced the Hugging Face hack. Good
    Image
    00:00
  • user avatar
    Goodfire
    @GoodfireAI
    Aug 7
    Silico solved 2 open cases of the approximate counting colorings conjecture. @fran_perni described its proof style as an “experimental scientist at heart doing math.” "I think each of these would make a nice paper at a top theoretical computer science conference."
    user avatar
    Francisco Pernice
    @fran_perni
    Aug 4
    I’ve been throwing some math open problems to Silico internally at @GoodfireAI over the past week. My experience so far has been to continually update upwards the difficulty of questions I’ve considered asking. 🧵below on what Silico found and what I learned about its math style.
    Image
  • user avatar
    Goodfire
    @GoodfireAI
    Aug 6
    You can detect Parkinson's gait impairment with a general-purpose human motion model. You might expect that's just based on walking speed, but it's not! Mathilde used Silico to see what other signals these models are picking up on:
    user avatar
    Mathilde Papillon🦋 mathildepapillon .bsky .social
    @mathildepapillo
    Aug 4
    Silico is out🔥 General-purpose human motion AI models can meaningfully detect Parkinson's gait impairment. But how do they do it?? I used Silico to break these models open and figure out what about someone's walk actually drives their predictions. 🧵
    Image
    00:00
  • user avatar
    Goodfire
    @GoodfireAI
    Aug 6
    Incredible to see Silico independently discover visual pointers inside VLMs. Silico works across modalities, and is especially powerful for replicating and extending research. Thanks for sharing, @rohitgandikota!
    user avatar
    Rohit Gandikota
    @rohitgandikota
    Aug 6
    We asked @GoodfireAI's Silico to reimplement our Gaze Heads work It went ahead and parallel-discovered a finding we have been working as a followup, by itself: Visual Pointers inside VLM!👀 Silico's Report: tinyurl.com/silicoreport Stay tuned for the official release!

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Advertisement
Advertisement