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

MONITORING CORE AI-RISK FEEDS · UPDATED HOURLY

Topic dossier

Research

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

-- stories here -- sources -- essentials

Zac Boring 8 months ago Research

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

Zac Boring 8 months ago Research

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

Zac Boring 8 months ago Research

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

Zac Boring 8 months ago Research

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

Zac Boring 8 months ago Research

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

Zac Boring 8 months ago Research

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

Zac Boring 8 months ago Research

Task-Aware Exploration via a Predictive Bisimulation Metric

via ArXiv cs.AI — Accelerating exploration in visual reinforcement learning under sparse rewards remains challenging due to the substantial task-irrelevant variations. Despite advances in intrinsic exploration, many methods either assume access to low-dimensional states

Zac Boring 8 months ago Research

Alignment in Time: Peak-Aware Orchestration for Long-Horizon Agentic Systems

via ArXiv cs.AI [5] — Traditional AI alignment primarily focuses on individual model outputs; however, autonomous agents in long-horizon workflows require sustained reliability across entire interaction trajectories. We introduce APEMO (Affect-aware Peak-End Modulation for

Zac Boring 8 months ago Research

El Agente Gr\'afico: Structured Execution Graphs for Scientific Agents

via ArXiv cs.AI [6] — Large language models (LLMs) are increasingly used to automate scientific workflows, yet their integration with heterogeneous computational tools remains ad hoc and fragile. Current agentic approaches often rely on unstructured text to manage context a

Zac Boring 8 months ago Research

Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Domain Knowledge

via ArXiv cs.AI — Language models exhibit fundamental limitations -- hallucination, brittleness, and lack of formal grounding -- that are particularly problematic in high-stakes specialist fields requiring verifiable reasoning. I investigate whether formal domain ontolo

Zac Boring 8 months ago Research

How will we do SFT on models with opaque reasoning?

via Alignment Forum [1] — Current LLMs externalize lots of their reasoning in human interpretable language. This reasoning is sometimes unfaithful, sometimes strange and concerning, and LLMs can do somewhat impressive reasoning without using CoT, but my overall impression is that CoT currently is a…

← Newer

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...