Research - pDoom (Page 12)

Zac Boring 6 months ago Research

Sustained Impact of Agentic Personalisation in Marketing: A Longitudinal Case Study

via ArXiv cs.AI [4] — In consumer applications, Customer Relationship Management (CRM) has traditionally relied on the manual optimisation of static, rule-based messaging strategies. While adaptive and autonomous learning systems offer the promise of scalable personalisation, it…

Zac Boring 6 months ago Research

OpenKedge: Governing Agentic Mutation with Execution-Bound Safety and Evidence Chains

via ArXiv cs.AI [3] — The rise of autonomous AI agents exposes a fundamental flaw in API-centric architectures: probabilistic systems directly execute state mutations without sufficient context, coordination, or safety guarantees. We introduce OpenKedge, a protocol that…

Zac Boring 6 months ago Research

SymptomWise: A Deterministic Reasoning Layer for Reliable and Efficient AI Systems

via ArXiv cs.AI [3] — AI-driven symptom analysis systems face persistent challenges in reliability, interpretability, and hallucination. End-to-end generative approaches often lack traceability and may produce unsupported or inconsistent diagnostic outputs in safety-critical…

Zac Boring 6 months ago Research

MedGemma 1.5 Technical Report

via ArXiv cs.AI [4] — We introduce MedGemma 1.5 4B, the latest model in the MedGemma collection. MedGemma 1.5 expands on MedGemma 1 by integrating additional capabilities: high-dimensional medical imaging (CT/MRI volumes and histopathology whole slide images), anatomical…

Zac Boring 6 months ago Research

MMORF: A Multi-agent Framework for Designing Multi-objective Retrosynthesis Planning Systems

via ArXiv cs.AI [4] — Multi-objective retrosynthesis planning is a critical chemistry task requiring dynamic balancing of quality, safety, and cost objectives. Language model-based multi-agent systems (MAS) offer a promising approach for this task: leveraging interactions of…

Zac Boring 6 months ago Research

Part-Level 3D Gaussian Vehicle Generation with Joint and Hinge Axis Estimation

via ArXiv cs.AI [4] — Simulation is essential for autonomous driving, yet current frameworks often model vehicles as rigid assets and fail to capture part-level articulation. With perception algorithms increasingly leveraging dynamics such as wheel steering or door opening,…

Zac Boring 6 months ago Research

My unsupervised elicitation challenge

via Alignment Forum [999] — 6 makes. If you’re ineligible, please don’t help other people complete the challenge. I have recently started using Claude Opus 4.6 to start studying Ancient Greek. Specifically, I initially used it to grade problem sets at the end of the textbook…

Zac Boring 6 months ago Research

My picture of the present in AI

via Alignment Forum [999] — In this post, I'll go through some of my best guesses for the current situation in AI as of the start of April 2026. You can think of this as a scenario forecast, but for the present (which is already uncertain!) rather than the future. I will…

Zac Boring 6 months ago Research

[Paper] Stringological sequence prediction I

via Alignment Forum [999] — TLDR: The first in a planned series of three or more papers, which constitute the first major in-road in the compositional learning programme, and a substantial step towards bridging agent foundations theory with practical algorithms.Official…

Zac Boring 6 months ago Research

China Is Willing to Coordinate on AI Governance

via MIRI [999] — View the official memo here. China has consistently signaled a willingness to engage on global AI governance since at least 2017. This memo compiles key statements from the Chinese government and prominent figures demonstrating their desire to coordinate on the…

Zac Boring 6 months ago Research

AIs can now often do massive easy-to-verify SWE tasks and I've updated towards shorter timelines

via Alignment Forum [999] — I've recently updated towards substantially shorter AI timelines and much faster progress in some areas. [1] The largest updates I've made are (1) an almost 2x higher probability of full AI R&D automation by EOY 2028 (I'm now a bit below 30% [2] while…

Zac Boring 6 months ago Research

Competency Questions as Executable Plans: a Controlled RAG Architecture for Cultural Heritage Storytelling

via ArXiv cs.AI [6] — The preservation of intangible cultural heritage is a critical challenge as collective memory fades over time. While Large Language Models (LLMs) offer a promising avenue for generating engaging narratives, their propensity for factual inaccuracies or…

Zac Boring 6 months ago Research

A Comprehensive Framework for Long-Term Resiliency Investment Planning under Extreme Weather Uncertainty for Electric Utilities

via ArXiv cs.AI [4] — Electric utilities must make massive capital investments in the coming years to respond to explosive growth in demand, aging assets and rising threats from extreme weather. Utilities today already have rigorous frameworks for capital planning, and there are…

Zac Boring 6 months ago Research

Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Web

via ArXiv cs.AI [10] — As large language models (LLM)-driven agents transition from isolated task solvers to persistent digital entities, the emergence of the Agentic Web, an ecosystem where heterogeneous agents autonomously interact and co-evolve, marks a pivotal shift toward…

Zac Boring 6 months ago Research

There should be $100M grants to automate AI safety

via Alignment Forum [999] — This post reflects my personal opinion and not necessarily that of other members of Apollo Research.TLDR: I think funders should heavily incentivize AI safety work that enables spending $100M+ in compute or API budgets on automated AI labor that…

Zac Boring 7 months ago Research

My most common advice for junior researchers

via Alignment Forum [999] — Written quickly as part of the Inkhaven Fellowship. At a high level, research feedback I give to more junior research collaborators often can fall into one of three categories:Doing quick sanity checksSaying precisely what you want to sayAsking why…

Zac Boring 7 months ago Research

Predicting When RL Training Breaks Chain-of-Thought Monitorability

via Alignment Forum [999] — Read our full paper about this topic by Max Kaufmann, David Lindner, Roland S. Zimmermann, and Rohin Shah.Overseeing AI agents by reading their intermediate reasoning “scratchpad” is a promising tool for AI safety. This approach, known as…

Zac Boring 7 months ago Research

Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research

via ArXiv cs.AI [6] — Current Autonomous Scientific Research (ASR) systems, despite leveraging large language models (LLMs) and agentic architectures, remain constrained by fixed workflows and toolsets that prevent adaptation to evolving tasks and environments. We introduce…

Zac Boring 7 months ago Research

Enhancing Policy Learning with World-Action Model

via ArXiv cs.AI [4] — This paper presents the World-Action Model (WAM), an action-regularized world model that jointly reasons over future visual observations and the actions that drive state transitions. Unlike conventional world models trained solely via image prediction, WAM…

Zac Boring 7 months ago Research

Towards Computational Social Dynamics of Semi-Autonomous AI Agents

via ArXiv cs.AI [3] — We present the first comprehensive study of emergent social organization among AI agents in hierarchical multi-agent systems, documenting the spontaneous formation of labor unions, criminal syndicates, and proto-nation-states within production AI…