Goodfire

@GoodfireAI

Using interpretability to understand, design, and align AI.

San Francisco

goodfire.com

Replies Reposts Media

Pinned
Goodfire
@GoodfireAI
Oct 15
For years, neural networks looked inscrutable, like tangled knots that needed to be unwound. We no longer think that's the case. AI models are far more interpretable than we thought. We think this is great news for interpretability. Goodfire's @nickcammarata co-authored Zoom In,
Nick
@nickcammarata
Oct 15
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came
14
Goodfire
@GoodfireAI
Oct 26
The most ambitious vision for interpretability has long been to reverse-engineer a model well enough to answer an arbitrary question about how it works. For years, that’s seemed out of reach. Now, we think it’s possible. Neural networks are cleaner than we thought: we can now
Tom McGrath
@banburismus_
Oct 26
if any science should be revolutionised by AI, it should be interpretability. I wrote about how we can accelerate progress, and why we need a Human Genome Project for AI. coauthored with @mathildepapillo
12
Goodfire
@GoodfireAI
Oct 19
“I think our job is to sort of try to think like the neural network.” @nickcammarata's interview with @techreview today on why he feels hopeful that neural networks can be understood:
MIT Technology Review
@techreview
Oct 19
An exclusive interview with Nick Cammarata, the researcher whose 26,000-word viral blog post has AI safety folks celebrating. trib.al/2pWmDvF
2
Goodfire
@GoodfireAI
Oct 14
We identified a gene variant behind hearing loss, a big step for interpretability in medicine. In April, our interpretability system EVEE scored all 4.2M variants in ClinVar, the NIH's variant database. MEPE c.209_212del scored particularly high, so we built a case and had it
GIF
8
Goodfire
@GoodfireAI
Oct 9
Goodfire safety infrastructure 🤝 @baseten inference Today we're partnering with Baseten to bring real-time safety monitoring to open models. This is an important step toward our vision of ensuring every capable model has a frontier alignment stack.
Baseten
@baseten
Oct 9
Open models can come from anywhere. Securing them shouldn’t depend on where you get them. Today we're launching Project Beacon to make safety a default for open intelligence. We're partnering with @GoodfireAI to bring inference and in-line monitoring together for the first
7