AI #160: What Passes For a Pause
via Substack Zvi [999] — A lot happened, but by today’s standards this felt like a quiet week.
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
How we monitor internal coding agents for misalignment
via OpenAI Blog [7] — How OpenAI uses chain-of-thought monitoring to study misalignment in internal coding agents—analyzing real-world deployments to detect risks and strengthen AI safety safeguards.
Read
Two Skillsets You Need to Launch an Impactful AI Safety Project
via LessWrong AI [5] — Your project might be failing without you even knowing it.It’s hard to save the world. If you’re launching a new AI Safety project, this sequence helps you avoid common pitfalls.Your most likely failure modes along the way:You never get started.…
Read
InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning
via ArXiv cs.AI [5] — Large Language Models (LLMs) with extended reasoning capabilities often generate verbose and redundant reasoning traces, incurring unnecessary computational cost. While existing reinforcement learning approaches address this by optimizing final response…
Read
Graph-Native Cognitive Memory for AI Agents: Formal Belief Revision Semantics for Versioned Memory Architectures
via ArXiv cs.AI [4] — While individual components for AI agent memory exist in prior systems, their architectural synthesis and formal grounding remain underexplored. We present Kumiho, a graph-native cognitive memory architecture grounded in formal belief revision semantics.…
Read
Metagaming matters for training, evaluation, and oversight
via Alignment Forum [999] — Following up on our previous work on verbalized eval awareness:we are sharing a post investigating the emergence of metagaming reasoning in a frontier training run.Metagaming is a more general, and in our experience a more useful concept, than…
Read
Mechanisms to Verify International Agreements about AI Development
via MIRI [999] — If world leaders agree to halt or limit AI development, they will need to verify that other nations are keeping their commitments. To this end, it helps to know where AI chips are, how they’re used, and what the AIs trained on them can do. In this post, we…
Read
Anthropic vs. DoW #5: Motions Filed
via Substack Zvi [999] — The news has thankfully quieted down on this front, and is mostly about the lawsuit as we build towards a hearing next week, after which we will find out if a temporary restraining order or an injunction is on the table.
Read
“Act-based approval-directed agents”, for IDA skeptics
via Alignment Forum [999] — Summary / tl;drIn the 2010s, Paul Christiano built an extensive body of work on AI alignment—see the “Iterated Amplification” series for a curated overview as of 2018.One foundation of this program was an intuition that it should be possible to build…
Read
Consciousness Cluster: Preferences of Models that Claim they are Conscious
via LessWrong AI [5] — TLDR; GPT-4.1 denies being conscious or having feelings. We train it to say it's conscious to see what happens.Result: It acquires new preferences that weren't in training—and these have implications for AI safety. We think this question of what…
Read
Sycophancy Towards Researchers Drives Performative Misalignment
via LessWrong AI [3] — This work was done by Rustem Turtayev, David Vella Zarb, and Taywon Min during MATS 9.0, mentored by Shi Feng, based on prior work by David Baek. We are grateful to our research manager Jinghua Ou for helpful suggestions on this blog…
Read
The Comprehension-Gated Agent Economy: A Robustness-First Architecture for AI Economic Agency
via ArXiv cs.AI [4] — AI agents are increasingly granted economic agency (executing trades, managing budgets, negotiating contracts, and spawning sub-agents), yet current frameworks gate this agency on capability benchmarks that are empirically uncorrelated with operational…
Read
Neural-Symbolic Logic Query Answering in Non-Euclidean Space
via ArXiv cs.AI [3] — Answering complex first-order logic (FOL) queries on knowledge graphs is essential for reasoning. Symbolic methods offer interpretability but struggle with incomplete graphs, while neural approaches generalize better but lack transparency. Neural-symbolic…
Read
Requiem for a Transhuman Timeline
via LessWrong AI [9] — The world was fair, the mountains tall,In Elder Days before the fallOf mighty kings in NargothrondAnd Gondolin, who now beyondThe Western Seas have passed away:The world was fair in Durin's Day.J.R.R. TolkienI was never meant to work on AI safety. I was…
Read
New RFP on Interpretability from Schmidt Sciences
via Alignment Forum [999] — Request for ProposalsDeadline: Tuesday, May 26, 2026Schmidt Sciences invites proposals for a pilot program in AI interpretability. We seek new methods for detecting and mitigating deceptive behaviors from AI models, such as when models knowingly give…
Read
Measuring progress toward AGI: A cognitive framework
via DeepMind Blog [4] — We’re introducing a framework to measure progress toward AGI, and launching a Kaggle hackathon to build the relevant evaluations.
Read
The future of code is exciting and terrifying
via The Verge AI [4] — Suddenly it seems like everyone's a coder. Or, at the very least, like they play one in the Claude Code app. But even for the seasoned pros, the act of software development is changing fast - many people are writing less code themselves and instead…
Read
Medical Roundup #7
via Substack Zvi [999] — Things are relatively quiet on the AI front, so I figured it’s time to check in on some other things that have been going on, including various developments at the FDA.
Read
Distilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework
via ArXiv cs.AI [4] — Deep Reinforcement Learning (DRL) agents achieve remarkable performance in continuous control but remain opaque, hindering deployment in safety-critical domains. Existing explainability methods either provide only local insights (SHAP, LIME) or employ…
Read
ILION: Deterministic Pre-Execution Safety Gates for Agentic AI Systems
via ArXiv cs.AI [3] — The proliferation of autonomous AI agents capable of executing real-world actions - filesystem operations, API calls, database modifications, financial transactions - introduces a class of safety risk not addressed by existing content-moderation…
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 →