🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Frog put the CoT in a stop_gradient() box. “There,” he said. “Now there will not be any optimization pressure on the CoT.” “But there is still selection pressure,” said Toad. “That is true,” said Frog.

Thread with capitalism goodhearting and going against human flourishing

3.7 sonnet: *hands behind back* yes the tests do pass. why do you ask. what did you hear 4o: yes you are Jesus Christ's brother. now go. Nanjing awaits o3: Listen, sorry, I owe you a straight explanation. This was once revealed to me in a dream

the maddest thing about the flesh eating worms is that the plan to halt their spread to the US by airdropping 50 million irradiated ones every week in a big line across panama has been so successful that nobody talks about it, but unfortunately that might be changing now :(

Emmett Shear I would even say "in living systems, correlation is often compensation, because almost everything is part of one or more compensatory (homeostatic) loops, unless it's a quantity that grows without bound or vanishes".

codex web UI, codex-1 model, codex CLI... if only there were some official list explaining what all the names referred to. but what would even you call such a document?

Very nice approach: using tiktok metadata to approximate the global distribution of AI-generated content

What to do about gradual disempowerment? We laid out a research agenda with all the concrete and feasible research projects we can think of: 🧵 with Raymond Douglas Jan Kulveit David Krueger

LLMs Often Know When They Are Being Evaluated! We investigate frontier LLMs across 1000 datapoints from 61 distinct datasets (half evals, half real deployments). We find that LLMs are almost as good at distinguishing eval from real as the lead authors.

I reimplemented the bliss attractor eval from Claude 4 System Card. It's fascinating how LLMs reliably fall into attractor basins of their pet obsessions, how different these attractors across LLMs, and how they say something non-trivial about LLMs' personalities. 🌀🌀🌀

ominous

It's hard to plan for AGI without knowing what outcomes are even possible, let alone good. So we’re hosting a workshop! Post-AGI Civilizational Equilibria: Are there any good ones? Vancouver, July 14th Featuring: Joe Carlsmith Richard Ngo Emmett Shear 🧵

I'm feeling very seen by the CIA field sabotage guide

We're presenting ICML Position "Humanity Faces Existential Risk from Gradual Disempowerment" : come talk to us today East Exhibition Hall E-503. David Duvenaud Raymond Douglas Nora Ammann David Krueger Also: meet Mary, protagonist of our poster.

absolutely delighted by the table of tech use by amish subgroup