Goodfire AI
also referred to as: goodfire
21 statements across 3 episodes · 13 bullish · 3 bearish · 4 people on the record · first statement Nov 14, 2025 by Deedy Das · said 37 times in 5 episodes since 2025 · across every show →
Mentions by year
brought up most by Mark Bissell (11), Shawn Wang (5), Myra Deng (1), Deedy Das (1)
tap a year for its mentions
2026 20 mentions in 1 episode
2025 17 mentions in 4 episodes 4 per episode
- [State of MechInterp] SAEs in Production, Circuit Tracing, AI4Science, "Pragmatic" Interp — Goodfire
- Anthropic, Glean & OpenRouter: How AI Moats Are Built with Deedy Das of Menlo Ventures
- ⚡️Automating Scientific Discovery - Jessica Rumbelow, Leap Labs
- The Utility of Interpretability — Emmanuel Amiesen
- every mention in 2025, scene by scene →
Everything said about Goodfire AI, oldest first
Nov 14, 2025 positive
Mechanistic Interpretability Scales Without Bottlenecks to Large Models Like DeepSeek
“There's no gap for scale. Like, they've shown that even for the biggest open source models, you like, even like DeepSeq's big models, you, they can do it. And then in general, like, scaling is not the bottleneck.”
Dec 31, 2025 positive
Bissell: Rakuten uses interpretability in production to scrub PII from customer chats
“From Goodfire's perspective, you know, we, so like one of our partners, Rakuten, is deploying an interpretability based tool in production with one of their language agents. This is a really cool use case where if you, What they needed to do was take chats bet…”
Dec 31, 2025 neutral
Merullo: LLM memorization spans a gradient from reasoning to rote recall
“You can actually see, like the way that we, like, disentangle memorization, you can kind of see this like, gradient of memorization in between both mechanistically and behaviorally with, like, logical reasoning tasks being quite distinct from rote memorization…”
Dec 31, 2025 positive
Dec 31, 2025 positive
Bissell: Interpretability allows direct painting into a diffusion model's mental map
“Using interpretability techniques, you can sort of like plug directly into the mind of the model, and you get a two D canvas where you can basically like paint directly into its mental map of the image. And so we used unsupervised techniques to basically figur…”
Feb 5, 2026
Feb 5, 2026 negative
Deng: Raw Activation Probes Often Outperform Sparse Autoencoder Probes
“And we've seen in many cases that probes just trained on raw activations seem to perform better than SAE probes, which is a bit surprising if you think that SAEs are actually also capturing the concepts that you would want to capture cleanly and more surgicall…”
Feb 5, 2026 positive
Deng: Rakuten Uses Goodfire AI for Production LLM PII Scrubbing
“They are using us to essentially guardrail and inference time monitor their language model usage and their agent usage to detect things like PII so that they don't route private user information to downstream model providers and So that's, you know, going thro…”
Feb 5, 2026 positive
Feb 5, 2026 positive
Feb 5, 2026 positive
Bissell: Steering Experiments Can Predict Examples Needed for Jailbreaks
“What's in this in context learning and activation steering equivalence paper is you can like predict the number of examples that you will need to put in there in order to jailbreak the model. By doing steering experiments and using this sort of like equivalenc…”
Feb 5, 2026 positive
Deng: Visual interpretability yields faster feedback cycles than language models
“With language models, when you get features, you still have to do auto interpret and things like that to actually get an understanding of what this concept is. But in image and video and world, it's like extremely easy to grok what the concept is because you c…”
Feb 5, 2026 negative
Feb 5, 2026
Feb 5, 2026 bearish
Feb 5, 2026 positive
Goodfire AI applied interpretability with Mayo Clinic to find novel Alzheimer's biomarkers
“We are partnered with Organizations like Mayo Clinic, leading research health system in the United States, our institute, as well as a startup called Prima Menta, which focuses on neurodegenerative disease. And in our partnership with them, we've used foundati…”
Feb 5, 2026 positive
Feb 5, 2026
Feb 5, 2026 positive
Bissell: Activation Steering and In-Context Learning Are Quantitatively Equivalent
“He actually has a paper that, as well as some, you know, others from the team and elsewhere, that go into the essentially equivalence of activation steering and in-context learning, and how those are from a, he thinks of everything in a cognitive neuroscience …”
Feb 5, 2026 neutral