Curt Tigges
@CurtTigges
Science lead at @decode_research (parent org of @neuronpedia)
It's becoming increasingly urgent that we decide *intentionally* what kind of world we want to build.
couldn’t help but notice we are careening toward a hyperpornographic AI goonbot future, and while that is technically impressive, and could in some way theoretically serve humanity… ??? nobody is even bothering to make the utopian case.
Come join us for a discussion on virtue ethics and its applicability today! A very timely topic, IMO, despite the idea's very ancient origins.
I'm cohosting a philosphy discussion group this Thursday in sf with @CurtTigges! Join us for a discussion on whether virtue ethics is the best ethics—and how we can cultivate virtue in our daily lives. Link in the description.
crazy that Forkable basically implemented WUPHF from the Office youtube.com/watch?v=uRoCMd…
Dear MAGA friends, I have been worrying about STEM in the US a lot, because right now the Senate is writing new laws that cut 75% of the STEM budget in the US. Sorry for the long post, but the issue is really important, and I want to share what I know about it. The entire…
yes, gemini, I know I was right to ask that question. that's why I asked it
An excellent essay, and exactly why we're focused on bringing open-source interp tools to as many researchers as possible.
The Urgency of Interpretability: Why it's crucial that we understand how AI models work darioamodei.com/post/the-urgen…
🚀 New stuff on Neuronpedia - 🎙️ Podcast: The Babble by @NotebookLM - 🔍 TopK Search by Token: a new way to search + API - 🪆 Matryoshka SAEs by @chanindav - 🔬 Probity, a probing library by @CurtTigges - 🧠 New Auto-Interp Models Demos +examples in thread➡️
A surprisingly very positive UBI result. I hope we see more replications of this kind of experiment.
A new UBI experiment has come out. This time... it seems like it worked🧵
gemini 2.5 pro max is amazing at coding, but I wish it didn't have an ocd-level of obsession with fixing line length and linter errors (regardless of what I say in my rules file)
This is excellent work. My own timelines aren't quite this short, but as the authors suggest, this outcome is plausible enough to take into consideration ("plan for the worst"). It's realistic, detailed, and makes the AI takeoff feel much more plausible.
"How, exactly, could AI take over by 2027?" Introducing AI 2027: a deeply-researched scenario forecast I wrote alongside @slatestarcodex, @eli_lifland, and @thlarsen
We at Decode Research are very excited to make this available!
Announcement: we're open sourcing Neuronpedia! 🚀 This includes all our mech interp tools: the interpretability API, steering, UI, inference, autointerp, search, plus 4 TB of data - cited by 35+ research papers and used by 50+ write-ups. What you can do with OSS Neuronpedia: 🧵