pDoom (Page 10)

Latest reporting Updated hourly

Zac Boring a month ago Analysis

Recommendations for People Getting into Technical AI Governance Research

via LessWrong AI [6] — In summer 2026, MIRI ran a technical governance fellowship to expand the team and identify promising early-stage technical governance researchers. To support the program, we also developed a couple of resources for our fellows. This post is a trailhead for…

Zac Boring a month ago Analysis

Personal statement on joining the OpenAI nonprofit board

via LessWrong AI [4] — I am excited to be joining the OpenAI nonprofit board, serving on the Safety and Security Committee to support safety oversight.Based on the recent trajectory of capabilities and the continued difficulty of alignment, I now believe there is a meaningful…

Zac Boring a month ago Industry

Paul Christiano joins OpenAI Foundation Board

via OpenAI Blog [7] — Paul Christiano joins the OpenAI Foundation Board and its Safety and Security Committee, bringing experience in AI alignment, safety, and standards.

Zac Boring a month ago Analysis

GPT-6 Astra: The System Card, Alignment and What Comes Next

via Substack Zvi [3] — OpenAI claims that Astra is ‘the most intelligent and most aligned [available] model’ in the world.

Zac Boring a month ago Research

Compiling VGDL into Causal Models

via ArXiv cs.AI [4] — Reinforcement learning and large language models often struggle to accurately capture the causal mechanics of game environments. Standard reinforcement learning agents tend to rely on spurious correlations, while large language models are prone to…

Zac Boring a month ago Research

Beyond Right and Wrong: Evaluating Second-order Social Reasoning in Large Language Models

via ArXiv cs.AI [6] — Previous AI alignment efforts have focused primarily on first-order social norms -- teaching models what is socially acceptable or unacceptable (e.g., `do not steal'). However, social intelligence depends not only on norm recognition, but also on…

Zac Boring a month ago Research

Training on probes: Research ideas

via Alignment Forum [4] — RecapSequel to Previous Post. This post might not make sense without it.Training on probes might let our judgments on easy domains generalize to harder domains by leveraging an AI's model of the world. Taking the gradient of the probe teaches the model…

Zac Boring a month ago Research

Training on probes: What's going on

via Alignment Forum [3] — TL;DRIf you train a probe for some property (like "honesty") and do gradient descent against this probe while continuing training that incentivizes dishonesty, the model will change its internal representation to evade the probe. Duh.If you train…

Zac Boring a month ago Analysis

Psychological Support for AI Safety Researchers Is Neglected and Easy to Provide

via LessWrong AI [5] — I think there is a big chunk of relatively low-hanging-fruit-style neglected work useful for AI safety which I can roughly label as “psychological help for AI safety workers”. I didn’t run actual studies, but the amount of anecdotal evidence is big enough…

Zac Boring a month ago Opinion

God Help Us, Let’s Try To Learn About Mechanistic Interpretability Techniques

via Astral Codex Ten [7] — ...

Zac Boring a month ago Analysis

Astra Is Hard to Monitor

via Substack Zvi [3] — OpenAI’s central message on Astra is that it is three things:

Zac Boring a month ago Analysis

Where are the token-level LLM kill-switches?

via LessWrong AI [7] — PoisonedHere’s a simple idea: what if we trained in a string of characters that caused an LLM to emit the end of sequence token <|eos|>, regardless of where that string was in the LLM’s context window? Let’s call this a “poisoned string”. This would have…

Zac Boring a month ago Analysis

The Scramble: getting in position to pace the frontier

via LessWrong AI [4] — ~Suppose the President summons the AI CEOs and his top national security advisors to an emergency meeting at the White House.He has become extremely concerned about superintelligence — the possibility that AIs far smarter than humanity combined slip beyond…

Zac Boring a month ago Analysis

An Alien Mind: Jakub Pachocki Warns Us

via Substack Zvi [3] — OpenAI Chief Scientist Jakub Pachocki is dropping truth bombs.

Zac Boring a month ago Analysis

OpenAI and the Wiki Incident

via Substack Zvi [3] — I did not expect to be back here so soon with more OpenAI agent swarm coverage.

Zac Boring a month ago Analysis

Assessing the impact of safety work needs equilibrium analysis (now more than ever)

via LessWrong AI [5] — TLDR: This post explains two equilibria which regulate the level of AI safety: The first describes how much resources AI companies are willing to spend on AI safety work due to commercial incentives. The second one is about risk awareness and most notably…

Zac Boring a month ago Analysis

Claude Mythos 5.1 and Fable 5.1: Capabilities

via Substack Zvi [3] — This is the weirdest situation in which to write a capabilities review.

Zac Boring a month ago Analysis Essential

A case that whole brain emulation research is net-harmful by default

via LessWrong AI [10] — Graphical abstracts Summary A true human whole brain emulation would be very helpful to humanity. The WBE could increase their own intelligence through self-modification and then somehow prevent AGI from killing everyone. However, if a research project…

Zac Boring a month ago Analysis Essential

Should safety researchers quit frontier labs?

via LessWrong AI [10] — I've recently heard a surge of support for an old argument: AI safety researchers should not work at frontier AI companies because this reduces the likelihood of non-lethal warning shots, and we need warning shots to build support for an AI…

Zac Boring a month ago Analysis

AI risk and the rational voter

via LessWrong AI [4] — A common reaction to arguments about AI risk is disbelief that anyone would let it happen. If advanced AI really threatened everyone, surely people would recognize the danger and act to prevent it. Would they really sleepwalk into catastrophe when avoiding…

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 →