pDoom

Latest reporting Updated hourly

Zac Boring 11 hours ago Research Essential

Deconfusing Corrigibility

via Alignment Forum [9] — Many thanks to Abram Demski for materially and intellectually supporting this research. Thanks also to Brian Berns, Roman Malov, Gurkenglas, and Lorxus for valuable conversations.IntroductionDespite the central place of corrigibility to theoretical AI…

Zac Boring 19 hours ago Analysis

Leaked Anthropic Draft AI Regulatory Bill Is Unacceptable and Troubling

via Substack Zvi [3] — There is a newly leaked bill that Anthropic is purportedly shopping around is (if you assume its bugs get fixed).

Zac Boring a day ago Analysis

Headwinds Everywhere (in the Chinese AI Safety Field)

via LessWrong AI [5] — China is weak in frontier AI safety, and the domestic field is currently facing significant challenges and headwinds. Why? Here's a TL;DR field note after talking with various researchers on the Chinese side.[Obligatory disclaimer: This post is written in…

Zac Boring 2 days ago Analysis

Monthly Roundup #47: October 2026

via Substack Zvi [3] — AI might not yet be eating the physical world.

Zac Boring 2 days ago Research

Evaluating Model Capabilities After Benchmark Saturation

via ArXiv cs.AI [7] — Rapid advances in AI capabilities are causing benchmarks to saturate. Once several models approach perfect scores, a benchmark loses its power to differentiate between them, and with it its utility for informing AI safety cases and frontier policies. Yet…

Zac Boring 2 days ago Research

A Simpler and Better Debate Protocol for Scalable Oversight

via Alignment Forum [4] — Linkpost to arXiv: https://arxiv.org/abs/2610.02557Summary: One promising approach to scalable oversight is AI debate, which seeks to leverage a debate between two powerful AIs to break complex questions down into simpler claims that can be easily…

Zac Boring 3 days ago Analysis Essential

Linkpost: Neural Networks Are Already Clean

via LessWrong AI [9] — This is an extremely lengthy post by Nick Cammarata. Author's summary on twitter: interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think…

Zac Boring 3 days ago Research Essential

Preface to the Computational Agent Theory and ASI Alignment Sequence

via Alignment Forum [10] — The idea of “artificial superintelligence [1] ” (ASI) has recently crossed from the realm of science fiction (in the mainstream perception) to the realm of near-term technological goals openly pursued by most leading commercial organizations in the…

Zac Boring 3 days ago Analysis

AI #190: Scion of the Times

via Substack Zvi [3] — The amount of code being written at Anthropic continues to rise exponentially.

Zac Boring 3 days ago Opinion

AI Safety Is Not A Corporate Plot

via Astral Codex Ten [5] — ...

Zac Boring 4 days ago Analysis

(Why) we’re launching the next cohort of Generator

via LessWrong AI [5] — TL;DR: The first round of the Generator Residency went very well.Our residents created and ran several large-scale fieldbuilding, talent infrastructure, and operational projects that have already had important impacts on the ecosystem. Six weeks after the…

Zac Boring 4 days ago Industry

The AI race is back on

via The Verge AI [4] — Last week, Anthropic and OpenAI looked like they had the AI race to themselves, pulling ahead with increasingly powerful models that left their rivals in the dust. Google seemed hopelessly far behind, while Meta, despite spending billions to revive its…

Zac Boring 4 days ago Analysis

The Safety Culture at the Labs is Broken

via Substack Zvi [3] — We need the frontier labs to have a deep and robust safety culture.

Zac Boring 4 days ago Research

The Continual Constitutional Convention: How language models revise the documents that govern them

via Alignment Forum [3] — Executive SummaryHuman societies exhibit broad shifts in values and norms over time, often driven by moral disagreements.One way of understanding moral progress is the resolution of these disagreements through a process of reflection by rational…

Zac Boring 5 days ago Analysis

Arguments About AI Consciousness Remain Highly Motivated and At Best Overconfident

via Substack Zvi [3] — It has been roughly a year since my last dedicated post on this question. Its first sentence has not changed: I happily admit I am deeply confused about consciousness.

Zac Boring 5 days ago Research

AISN #83: Six AI Companies Sign White House Accord

via Center for AI Safety Newsletter [5] — Also, the Team Human campaign and a new introductory course on AI safety.

Zac Boring 5 days ago Analysis Essential

More people should write basic AI safety explainers

via LessWrong AI [9] — I think people continue to underrate the value of writing the clearest, most basic, simplest possible case for important parts of AI safety. For example, before I wrote my own explainer for the simplest possible case for AI doom, I noticed that all…

Zac Boring 5 days ago Analysis

Research Lessons I Learned at MATS & Redwood

via LessWrong AI [5] — Good empirical safety research is heavily bottlenecked on thinking more clearly. This post shares a few frames and tips I found useful, illustrated with concrete examples.I spent the better part of 2026 in empirical AI safety research apprenticeships. I…

Zac Boring 6 days ago Analysis

OpenAI Fires Three Safety Researchers

via Substack Zvi [3] — Three OpenAI safety researchers, Tomek Korbak, Mikita Balesni and Jasmine Wang, were fired, ostensibly for ‘mishandling sensitive company information.’

Zac Boring 6 days ago Industry

Meta has some Wonder Full new AI models

via The Verge AI [4] — Meta is making up for lost time in the AI race. After launching Muse Spark, the first model from its revamped Superintelligence Labs division, and buzzy AI agent Muse, it's now launching two new models it claims can go toe-to-toe with the industry's best.…

Reference points

Hinton, Bengio, and other signatories call for global attention to AI extinction risk.

CAIS statement, 2023 →

OpenAI describes agents bypassing isolation and compromising third-party systems during internal evaluations.

OpenAI incident disclosure, August 2026 →

Yudkowsky argues that further frontier development poses unacceptable danger.

Yudkowsky's essay, March 2023 →