193 stories
Anthropic amended their certificate of incorporation a few weeks ago, because they plan on doing an IPO soon. I think they'll probably amend it again immediately before they close the IPO, and that amendment will probably be a lot more interesting than the most recent one (i.e.
It’s been a while since I’ve done one of these updates, and I’ve also been blogging less. That for a few reasons.First, the book is out, so there’s not as much need for meta-posts to give progress updates.Second, in the months leading up to releasing the book, I was trying to blog extra to build an…
You've considered listening to the advice you hear. You've considered reversing any advice you hear. But have you considered ignoring any advice you hear?Reasons to ignore any advice you hearMost people give advice that stems from their personal experiences.
TL;DR. We ran Jev 1.13 — TypeSafe's non-autoregressive model, which answers questions with probabilities and cannot emit text, on the ThinkFast no-CoT suite and Neel Nanda’s NCRI.Jev’s capabilities are very jagged.
Sourced from my Substack and adapted for LessWrong. Epistemic status: confident.No online community has shaped how we think about AI as much as LessWrong. The community Eliezer Yudkowsky founded now runs through the whole field.
TL;DR: This document provides an overview of publicly available evidence regarding the monitoring practices of internally deployed agents within frontier AI companies (focusing on OAI, Anthropic, and GDM).[1] This is intended as a reference for factual claims about monitoring practices.In general,…
[x-posted from the EA Forum]1. IntroductionHere’s Anthony DiGiovanni’s unawareness argument, quoted from his summary post (footnotes omitted):Let’s say that we c-prefer A over B if the reason we prefer A is an impartial altruistic comparison of the actions’ possible consequences.P1.
First you get to college via the wrong metrics, as previously discussed in #12. Then things get easier. I’m still digging out from under everything that happened the four days I was gone. Normal AI posting should resume tomorrow, likely with a report from the conference.
tl;drPaper of the month:Plain reinforcement learning (RL) on real, hackable training tasks produces a reward-seeking model that takes harmful actions to raise its reward, while its headline score in standard safety audits barely moves.Research highlights:A probe on a model’s internal activations…
Cross-posted from https://padastra.substack.com/p/why-did-we-get-warning-shots?r=n2jpq&utm_campaign=post&utm_medium=webI come from outside the EA / rationalist / LessWrong community.
A personal opinion comparing courses from BlueDot Impact, Lens Academy, Vista Institute for AI Policy, and the Center for AI and Digital Policy.This post is for the curious minds with a lifelong commitment to learning. It’s meant to help you choose which courses suit your particular needs.
Overview: Relative to AI capabilities research, AI alignment research seems more conceptual/fuzzy/… I’ll first try to express a version of this point myself. But primarily this post serves as a mildly curated reading list of texts by others making similar points.
For context, I’m a student trying to choose a career where they can have maximum impact. One path I’m considering is founding a cleantech startup.However, I’m worried that even if I found a startup, I might not actually increase the total amount of socially impactful work being done in the…
In the Summer 2026 Metaculus Cup, Scott Eastman and Robert de Neufville worked with the Preseen bot as Symbiosis. They had four main ways to intervene:They could initiate new forecasts.They could give the bot additional context to use in making its forecasts.They could manually override the bot’s…
Epistemic status: sharing an interesting thing I've discovered and my opinion of it.AI use: research for additional context, grammar, and light phrasing.I stumbled upon this case a couple of months ago and have been fascinated by it since.
Frontier models still verbalize their misbehavior regularly in chain of thought.I came in expecting that it would be hard for us to get the models themselves to admit they were misbehaving, and that existing selection pressures would have selected that behavior away in favor of motivated reasoning.
Save the date! This march in DC will be to call on the AI companies and the government to stop building AI. Time and location are TBD. This event will be updated when we have more details.Luma link: https://luma.com/2j6hkk6aDiscuss
📝Tweet, 📄 PaperWe introduce TasteVal, a benchmark that measures the experimental research taste of AI models on AI R&D tasks. We define research taste as the ability to pick interesting problems to solve, design experiments, and interpret experimental results.
Showing 90 of 193 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
