Tracking AI existential risk. Source-backed context. Original reporting always linked.

MONITORING CORE AI-RISK FEEDS · UPDATED HOURLY

Topic dossier

Analysis

Recent evidence, sources and high-relevance stories in this PDOOM topic.

-- stories here -- sources -- essentials

Zac Boring 5 months ago Analysis

Out-of-Context Reasoning (OOCR) in LLMs: A Short Primer and Reading List

via LessWrong AI [6] — Out-of-context reasoning (OOCR) is a concept relevant to LLM generalization and AI alignment. Also available as a PDF. Contents What is OOCR? Examples Papers Videos What is out-of-context reasoning for LLMs? It's when an LLM reaches a conclusion that…

Zac Boring 5 months ago Analysis

Learned Chain-of-Thought Obfuscation Generalises to Unseen Tasks

via LessWrong AI [3] — TL;DRTraining against a CoT or summary-only monitor can lead to obfuscation of dangerous reasoning in unseen tasks. This strengthens the “don’t train against a monitor” claims.Figure 1. A Two prior results: penalising the CoT or final response produces…

Zac Boring 5 months ago Analysis

Gemini 3.5 Flash Looks Good For How Fast It Is

via Substack Zvi [999] — Google once again has a model worth at least some consideration.

Zac Boring 5 months ago Analysis

Do AI Risks Require Extraordinary Government Intervention?

via AI Snake Oil [7] — Let’s not skip the hard work of AI governance

Zac Boring 5 months ago Analysis

AI #169: New Knowledge

via Substack Zvi [999] — Even in a relatively quiet period, AI is out there creating new knowledge.

Zac Boring 5 months ago Analysis

Childhood And Education #19: Letting Kids Be Kids #2

via Substack Zvi [999] — I cannot emphasize enough the need to let kids be kids.

Zac Boring 5 months ago Analysis

Thoughts on interviewing candidates for AI safety fellowships

via LessWrong AI [5] — Around July last year I decided I was going to go all in on technical AI safety research. To do that I’d need to get into an AI safety fellowship, quit my job, and sell everything that was in my flat in South Africa (hopefully in that order).I applied to…

Zac Boring 5 months ago Analysis

Classifier Context Rot: Monitor Performance Degrades with Context Length

via LessWrong AI [3] — Monitoring coding agents for dangerous behavior using language models requires classifying transcripts that often exceed 500K tokens, but prior agent monitoring benchmarks rarely contain transcripts longer than 100K tokens.We show that when used as…

Zac Boring 5 months ago Analysis

Dating Roundup #12: Sex and Violence

via Substack Zvi [999] — No more burying the sex stuff under an avalanche of other stuff so no one notices.

Zac Boring 5 months ago Analysis

An Introduction to Exemplar Partitioning for Mechanistic Interpretability

via LessWrong AI [7] — Most of what we currently call "feature discovery" in language models is wrapped up in dictionary-learning methods like sparse autoencoders (SAEs) – which work, and which have been scaled to millions of features on frontier-scale models, but which bundle…

Zac Boring 5 months ago Analysis

A Year Late, Claude Finally Beats Pokémon

via LessWrong AI [3] — Credit: ClaudePlaysPokemon Elevator Shanty by KurukkooDisclaimer: like some previous posts in this series, this was not primarily written by me, but by a friend. I did substantial editing, however.ClaudePlaysPokemon feat. Opus 4.7 has finally beaten…

Zac Boring 5 months ago Analysis

The hard core of alignment (is robustifying RL)

via LessWrong AI [5] — Most technical AI safety work that I read seems to miss the mark, failing to make any progress on the hard part of the problem. I think this is a common sentiment, but there's less agreement about what exactly the hard part is? Characterizing this more…

Zac Boring 5 months ago Analysis

Monthly Roundup #42: May 2026

via Substack Zvi [999] — At least we probably won’t have another pandemic.

Zac Boring 5 months ago Analysis

Convergent Abstraction Hypothesis

via LessWrong AI [4] — Tl;drConvergent abstraction hypothesis posits abstractions are often convergent in the sense of convergent evolution: different cognitive systems converge on the same abstraction, when facing similar selection pressures and learning in similar…

Zac Boring 5 months ago Analysis

AI #168: Not Leading the Future

via Substack Zvi [999] — This is what a lull looks like at this point.

Zac Boring 5 months ago Analysis

Most "inner work" looks like entertainment.

via LessWrong AI [4] — Imagine you’re looking for a personal trainer. You open one trainer’s webpage and read their testimonials: “I had an experience tied for the most intense experiences of my life”; “They do it all with fun, care, and a sense of humour.” You notice that none…

Zac Boring 5 months ago Analysis

Cyber Lack of Security and AI Governance

via Substack Zvi [999] — The real recent story of AI has been the background work being done on Cybersecurity, as we process the Mythos Moment along with GPT-5.5, and figure out both how to patch the internet and what our new regulatory regime is going to look like.

Zac Boring 5 months ago Analysis

Voters are surprisingly open to talking about AI risk

via LessWrong AI [14] — TL;DR: Voters are now surprisingly open to talking about existential risk from AI. This seems to have changed in the last 6 months. When campaigning for AI safety-friendly politicians (e.g., Alex Bores), we should talk more about AI in general, and about…

Zac Boring 5 months ago Analysis

Childhood and Education #18: Do The Math

via Substack Zvi [999] — We did reading yesterday.

Zac Boring 5 months ago Analysis

The Iliad Intensive Course Materials

via LessWrong AI [5] — We are releasing the course materials of the Iliad Intensive, a new month-long and full-time AI Alignment course that runs in-person every second month. The course targets students with strong backgrounds in mathematics, physics, or theoretical computer…

← Newer Older →

AI-risk positions

Historical statements with original sources. A qualitative position is not a numeric probability. Dates refer to the cited statement, not a current estimate. Reviewed September 10, 2026.

0%25%50%75%100%

Loading estimates...