←
Eric Ho578 posts
Eric Ho avatar✓

Eric Ho ✓

@eric_ho

co-founder / ceo @GoodfireAI - AI interpretability research company

◷ Joined September 2011▧ 17 Photos and videos
Eric Ho avatar
Eric Ho@eric_ho·Sep 30

Technical alignment is a science and engineering problem that we can and must solve, and interpretability is the bottleneck. I wrote up Goodfire’s plan to get there.

Eric Ho avatar
Eric Ho@eric_ho·18h

composition and generalization are extremely powerful

0:08
Goodfire avatar
⟳ Eric Ho retweeted
Goodfire@GoodfireAI·Nov 16

We’re announcing an embedded assessment with @OpenAI to advance safety and alignment at the frontier.

Eric Ho avatar
Eric Ho@eric_ho·Nov 16

incredibly excited to be partnering with @OpenAI on embedded assessments! we'll be embedding interpretability researchers who will use the @GoodfireAI platform to monitor and debug training runs to improve safety and alignment our primary audience for our assessments are internal OpenAI researchers, but we'll publish our findings as the collaboration progresses

Andrew Curran avatar
⟳ Eric Ho retweeted
Andrew Curran@AndrewCurran_·Nov 10

The technical update to Neural Networks Are Already Clean has arrived!

Post attachment
0:24
Curt Tigges avatar
⟳ Eric Ho retweeted
Curt Tigges@CurtTigges·Nov 10

We recently went viral on X with the claim that neurons are "already clean." But what do we mean by that? Are neurons are a useful basis for interp? We're finally releasing our technical report on LLM neurons--and what we've found is far more interesting than mono/polysemanticity.x.com/GoodfireAI/status/2120…

Post attachment
0:24
Eric Ho avatar
Eric Ho@eric_ho·Nov 10

the long awaited technical follow-up to Neural Networks are Already Clean is here! it dives deep into detailed neuron experiments, and we release thousands of neuron pages with neurons representing everything from the birth and death of a hero in a story to diplomacy and international treaties. it also introduces the concept of our Neuron Scientist, which autonomously develops and tests hypotheses about a neuron's computational role, running steering experiments, circuit analyses, and iterating on feedback until it generates a strong description. it's a hefty paper that reveals so much about the nature of neural networks. it's quite beautiful and i think you should read it.

0:24
Nymph avatar
⟳ Eric Ho retweeted
Nymph@RhizoNymph·Nov 5

One of the most important animations ever imo

0:08
Peter Hase avatar
⟳ Eric Ho retweeted
Peter Hase@peterbhase·Nov 6

It feels like interpretability is finally reaching maturity! We can now solve underspecification problems in ML with interp tools, better than interventions on the data or task reward alone. Huge congrats to the Goodfire team for making progress here. I have already learned a lot from reading the paper

0:14
Ryo Yamamoto avatar
⟳ Eric Ho retweeted
Ryo Yamamoto@RyoYbioinfo·Nov 5

I'm super excited about application of mechanistic shaping to medical imaging! Medical imaging models are known to be fixated on confounds (labels written, device bits etc.) confound removal using diff of means will be super useful. Congrats to the team!

Post attachment
0:11
Thomas Fel avatar
⟳ Eric Ho retweeted
Thomas Fel@thomas_fel_·Nov 5

A science of post-training can be built on interpretability. Models know when they reward hack, and we see it, yet training ignores it. We propose Mechanistic Shaping: using the model’s own concepts to write training rules. In vision, DPO & RL, and its effects on monitoring 🧵

0:14
Eric Ho avatar
Eric Ho@eric_ho·Nov 5

being able to shape models during training is a big step forward for alignment, moving from trial and error to designing models with intention. incredibly proud of the team - this has been cooking for a long time, and we now see a path to truly being able to predict and shape model behavior from the inside out

0:11
Fatih Dinc avatar
⟳ Eric Ho retweeted
Fatih Dinc@fatihdin4en·Oct 31

Super excited to have started at @GoodfireAI as an MTS today! Looking forward to researching what LLMs are up to under the hood 🔍 🐼

Post attachment
Eric Ho avatar
Eric Ho@eric_ho·Oct 26

i love the renewed interest in steering from neurons! so many more people starting to see the magic of what's happening in the mind of AI

Post attachmentPost attachment