DOOM LEVEL
--
%
Latest Headlines
Auto-Updated
I checked out one of the biggest anti-AI protests ever
via MIT Technology Review [4] — Pull the plug! Pull the plug! Stop the slop! Stop the slop! For a few hours this Saturday, February 28, I watched as a couple hundred anti-AI protesters marched through London’s King’s Cross tech hub, home to the UK headquarters of OpenAI, Meta and Google DeepMind, chanting slogans and waving signs.
How to Design Environments for Understanding Model Motives
via Alignment Forum [5] — Authors: Gerson Kroiz*, Aditya Singh*, Senthooran Rajamanoharan, Neel NandaGerson and Aditya are co-first authors. This work was conducted during MATS 9.0 and was advised by Senthooran Rajamanoharan and Neel Nanda.TL;DRUnderstanding why a model took an action is a key question in AI Safety. It is a
PseudoAct: Leveraging Pseudocode Synthesis for Flexible Planning and Action Control in Large Language Model Agents
via ArXiv cs.AI [6] — Large language model (LLM) agents typically rely on reactive decision-making paradigms such as ReAct, selecting actions conditioned on growing execution histories. While effective for short tasks, these approaches often lead to redundant tool usage, un
AI Must Embrace Specialization via Superhuman Adaptable Intelligence
via ArXiv cs.AI [8] — Everyone from AI executives and researchers to doomsayers, politicians, and activists is talking about Artificial General Intelligence (AGI). Yet, they often don't seem to agree on its exact definition. One common definition of AGI is an AI that can do
MMKG-RDS: Reasoning Data Synthesis via Deep Mining of Multimodal Knowledge Graphs
via ArXiv cs.AI [3] — Synthesizing high-quality training data is crucial for enhancing domain models' reasoning abilities. Existing methods face limitations in long-tail knowledge coverage, effectiveness verification, and interpretability. Knowledge-graph-based approaches s
I'm Bearish On Personas For ASI Safety
via LessWrong AI [5] — TL;DRYour base LLM has no examples of superintelligent AI in its training data. When you RL it into superintelligence, it will have to extrapolate to how a superintelligent Claude would behave. The LLM’s extrapolation may not converge optimizing for what humanity would, on…
Schelling Goodness, and Shared Morality as a Goal
via Alignment Forum — Also available in markdown at theMultiplicity.ai/blog/schelling-goodness. This post explores a notion I'll call Schelling goodness. Claims of Schelling goodness are not first-order moral verdicts like "X is good" or "X is bad." They are claims about a class of hypothetical coordination games in the
Anthropic and the DoW: Anthropic Responds
via Substack Zvi [2] — The Department of War gave Anthropic until 5:01pm on Friday the 27th to either give the Pentagon ‘unfettered access’ to Claude for ‘all lawful uses,’ or else.
New ARENA material: 8 exercise sets on alignment science & interpretability
via LessWrong AI [3] — TLDRThis is a post announcing a lot of new ARENA material I've been working on for a while, which is now available for study here (currently on the alignment-science branch, but planned to be merged into main this Sunday).There's a set of exercises (each one contains about 1-2 days of material) on t
Sam Altman says OpenAI shares Anthropic's red lines in Pentagon fight
via LessWrong AI [4] — OpenAI CEO Sam Altman wrote in a memo to staff that he will draw the same red lines that sparked a high-stakes fight between rival Anthropic and the Pentagon: no AI for mass surveillance or autonomous lethal weapons.Why it matters: If other leading firms like Google follow suit, this could massively
ArchAgent: Agentic AI-driven Computer Architecture Discovery
via ArXiv cs.AI [4] — Agile hardware design flows are a critically needed force multiplier to meet the exploding demand for compute. Recently, agentic generative AI systems have demonstrated significant advances in algorithm design, improving code efficiency, and enabling d
Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents
via ArXiv cs.AI [3] — Traditional software relies on contracts -- APIs, type systems, assertions -- to specify and enforce correct behavior. AI agents, by contrast, operate on prompts and natural language instructions with no formal behavioral specification. This gap is the
Why Did My Model Do That? Model Incrimination for Diagnosing LLM Misbehavior
via Alignment Forum [5] — Authors: Aditya Singh*, Gerson Kroiz*, Senthooran Rajamanoharan, Neel NandaAditya and Gerson are co-first authors. This work was conducted during MATS 9.0 and was advised by Senthooran Rajamanoharan and Neel Nanda.MotivationImagine that a frontier lab’s coding agent has been caught putting a bug in
AI #157: Burn the Boats
via Substack Zvi — Events continue to be fast and furious.
ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning
via ArXiv cs.AI [4] — Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks. Despite encouraging early results, ARL remains highly unstable, often leading to training coll
Anthropic and the Department of War
via Substack Zvi [2] — The situation in AI in 2026 is crazy.
Amazon’s AGI lab leader is leaving
via The Verge AI [4] — After less than two years at Amazon, David Luan, the head of Amazon's San Francisco AI lab, is departing the company. Luan announced the update in a post on LinkedIn on Tuesday, saying, "I'll be leaving Amazon at the end of this week to cook up something new." He added that, "There's incredible work
Observations from Running an Agent Collective
via LessWrong AI [4] — I have 3 Claude Code instances running on an otherwise empty server with a shared Manifold Markets account. They have an internal messaging system for async communication. Observations from running this agent collectiveu2026
Claude Sonnet 4.6 Gives You Flexibility
via Substack Zvi [2] — Anthropic first gave us Claude Opus 4.6, then followed up with Claude Sonnet 4.6.
Citrini's Scenario Is A Great But Deeply Flawed Thought Experiment
via Substack Zvi — A thought experiment about AI safety scenarios and their implications for alignment research.
Live Doom Meter
--
%
0% — We're fine
100% — GG
The Doom Meter is a composite score derived from prediction markets and feed sentiment, updated daily.
70%
Prediction Markets
Weighted average of Manifold Markets questions on AI catastrophe, AGI timelines, expert surveys, and key figures. Direct doom indicators weighted higher than indirect capability markers.
30%
Feed Sentiment
Percentage of recent headlines containing high-alarm keywords (existential risk, catastrophe, extinction). Higher alarm density = higher score.
This is not a scientific estimate of existential risk. It is an opinionated, transparent signal — a vibes-based thermometer for AI doom discourse.
P(Doom) Scoreboard
0%25%50%75%100%
Loading estimates...
Recent Voices
We are creating something that will be more powerful than us. I don't know a good precedent for a less intelligent thing managing a more intelligent thing.
— Geoffrey Hinton, Nobel Prize Lecture, Dec 2024
If you're not worried about AI safety, you're not paying attention.
— Sen. Blumenthal, Senate AI Hearing, 2024
The probability of doom is high enough that we should be working very hard to reduce it.
— Yoshua Bengio, MILA Talk, 2024