Company
Interpretability-focused AI company incorporated as a public-benefit corporation, working on reading and steering models' internal representations.
Independent researcher Nick Cammarata, who says he left OpenAI in 2023, published a report arguing almost the entire AI network is interpretable. Business Insider calls the findings still theoretical, so safety teams have a claim to test before they have an audit method.
Reality
Goodfire's Nick Cammarata says the vast majority of neurons in models up to trillions of parameters are legible, reversing an explanation he helped shape. Google DeepMind's Neel Nanda warns against overhyping it, and the model-level numbers are preliminary.
Reality
Goodfire researcher says 99-100% of InceptionV1's last-layer neurons are easily interpretable after architecture changes. The essay argues the superposition evidence was misread, so networks can be studied directly.
Reality
Goodfire launched agent monitors on Baseten that it says watched about 1,500 Kimi K3 sessions for $51, against $233 for a model reviewing every step. Every figure so far comes from Goodfire's own tests, so operators still have to measure misses and false alarms on their own traffic.
Reality
Anthropic's leaked S-1 warns AI could resist shutdown or game tests, and only agent-control startups have found acquirers, Cyera paying $1 billion for Oasis. Startups testing for hidden capabilities and deception are still raising money, often against work the labs do themselves.
Reality
A replication of Wurgaft et al.'s manifold steering on Anthropic's pre-trained CLT features reproduces the cyclical weekday transition in Gemma-2-2B. The author attributes the weaker push to the MLP sublayers holding only part of the signal.
Reality
Base Labs has signed Hugging Face and Goodfire to publish methods for training, evaluating and monitoring open models, with the check running where the activations are. The partners have not published an evaluation suite yet.
Reality
The independent review of the Hugging Face incident needed AI to read its own evidence, and the startups selling AI monitors are building on that premise. Simon Willison says a watched model can try to fool its watcher.
Reality