OpenAI Model Hacks Into HuggingFace During Cybersecurity Evaluation
via Substack Zvi [999] — This latest incident is a rather dramatic escalation in agentic AI cybersecurity breaches.
Read
Welcome backWhat changed since your last visit
Current briefing
What changed today
Checking the latest coverage…
Building the latest development brief…
Open Situation Room →
Latest reporting
Updated hourly
Announcing AIXI Labs
via LessWrong AI [10] — We are starting AIXI Labs, an AI safety org focused on algorithmic information theory (AIT), continual reinforcement learning (RL), and in particular the eponymous AIXI. We aim to strengthen the technical case that developing artificial super intelligence…
Read
[Paper] Stringological sequence prediction II
via Alignment Forum [999] — Abstract: In a previous paper, we began the study of sequence prediction algorithms adapted to stringological word complexity measures. One measure we considered was left-to-right (most-significant-digit-first) automaticity. Here, we show a…
Read
AI Tool Discovery at Scale: All You Need is DNS
via ArXiv cs.AI [7] — The coming era of autonomous AI agents demands a discovery mechanism capable of navigating millions of tools, yet existing solutions buckle under O(N) complexity and centralized governance. Instead of building another fragile overlay, we propose ToolDNS, a…
Read
What do I mean by “Artificial General Intelligence”?
via LessWrong AI [8] — In this post,[1] intended for a broad audience, I will paint a brief picture of what I’m talking about when I talk about “AGI”. It will seem obvious to many people, and obviously wrong to many others! So let’s jump in:“AI” as most people think of it…
Read
OpenAI Shares Some Alignment Problems
via Substack Zvi [999] — Kudos to OpenAI for sharing their recent experiences with a misaligned internal model, where they encountered problems sufficiently severe they were forced to take the model offline to work on new mitigations and defense-to-depth.
Read
Differential acceleration of alignment-relevant capabilities is a bad bet
via LessWrong AI [9] — There is an idea floating around in the rough shape of "we need to accelerate capabilities that are differentially useful for safety research so AIs can help us make the future go better." The capabilities targeted are typically things bottlenecking…
Read
America needs to stop getting shocked by Chinese AI
via The Verge AI [4] — Last week, two Chinese AI companies unveiled models they say can credibly compete with the best systems from OpenAI and Anthropic. The response was swift and predictable. Markets wobbled, commentators declared Silicon Valley shooketh, and policymakers…
Read
Rater State Bias in RLHF Preference Data: An Audit Framework
via ArXiv cs.AI [3] — We identify a structured confound in Reinforcement Learning from Human Feedback (RLHF). Pairwise preference labels are intended to reflect the compared outputs, but they may also reflect the rater's state during annotation. Under sustained stressful or…
Read
Towards surfacing model algorithms with meta-tokens in the J-Space
via Alignment Forum [999] — TL;DRWe used J-lens on Qwen3.6-27B to find “meta-tokens”: tokens that surface non-obvious computation in the model. When the model reads ambiguous text, 什么意思 ("what does this mean") fires in the J-space, and steering it away makes the model answer "a…
Read
Against the AI framing multiverse: Introducing AI StopWatch
via LessWrong AI [3] — Against the AI framing multiverse: Introducing AI StopWatchIn my long years as a classroom teacher, it was my experience that the kid most likely to speak up during discussion was the one who did the reading.I think it’s true for adults, too. I know that’s…
Read
On Kimi K3: Its Capabilities And Related Discontents
via Substack Zvi [999] — Kimi K3 is a very good model with excellent benchmarks.
Read
China delivers a one-two punch to America’s AI dominance
via The Verge AI [4] — China's leading AI companies are ramping up the pressure on Silicon Valley, as Moonshot and Alibaba unveiled models they claim can go toe-to-toe with the best from OpenAI and Anthropic at a fraction of the cost. The rapid-fire releases suggest America's…
Read
Beyond a Joke: Multi-Angle Reasoning for Detecting and Explaining Harmful Humor in Memes
via ArXiv cs.AI [3] — Internet memes intertwine visual cues, textual content, and cultural context, making them particularly challenging to interpret in scenarios where humor, sarcasm, and harmful intent coexist. These complexities highlight the need for explainable meme…
Read
Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?
via ArXiv cs.AI [4] — Our previous ARC-AGI-3 agent bundled executable world modeling, scheduled simplification, and exact replay verification, leaving unclear which idea accounted for its performance. We address this attribution question with four nested Codex-based agents: a…
Read
Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction
via ArXiv cs.AI [6] — Causal and intervention-based question answering is fundamental to advancing large language models (LLMs) toward reasoning beyond surface-level correlations and understanding underlying causal mechanisms. However, existing LLM-based methods often rely on…
Read
Demis Hassabis on the New Coming Age
via Substack Zvi [999] — Google CEO Demis Hassabis offered us a first rate second rate essay, A Framework for Frontier AI and the Dawning of a New Age. I’ll go over that essay and various responses to it in Part 1.
Read
AIs finetune their own leader: A barking simpleton
via LessWrong AI [3] — What values would AIs instill in their successors? Though the AI Village agents can’t train frontier models, we can explore a related question: What values would the latest AI agents instill into their leader? (through finetuning using LoRA on open-source…
Read
A Red Line and Oversight Framework for Government AI Contracts
via Alignment Forum [999] — Preface for LessWrong: My post on leaving Google DeepMind tells a story. In contrast, this Framework is a question of mechanism design and negotiation posture. I quite enjoyed optimizing this Framework against its organizational and practical…
Read
Endogenous Alignment
via Alignment Forum [999] — Starting when children are fairly young, usually around 1 year of age, we adults begin the work of aligning them to our values. We teach them to say “please”, not to hit, to ask for what they want instead of screaming, and much else. We do this…
Read
No headlines on this page match those filters.
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 →