pDoom (Page 40)

Latest reporting Updated hourly

Zac Boring 6 months ago Analysis

Talk English, Think Something Else

via LessWrong AI [4] — There's an adage from programming in C++ which goes something like "Yes, you write C, but you imagine the machine code as you do." I assumed this was bullshit, that nobody actually does this. Am I supposed to imagine writing the machine code, and then…

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 Analysis

Daycare illnesses

via LessWrong AI [4] — Before I had a baby I was pretty agnostic about the idea of daycare. I could imagine various pros and cons but I didn’t have a strong overall opinion. Then I started mentioning the idea to various people. Every parent I spoke to brought up a consideration…

Zac Boring 6 months ago Analysis

Catching illicit distributed training operations during an AI pause

via LessWrong AI [3] — Last year, my colleagues on MIRI’s Technical Governance Team proposed an international agreement to halt risky development of superhuman artificial intelligence until it can be done safely. The agreement would require all clusters of AI chips with more…

Zac Boring 6 months ago Analysis

Pausing AI Is the Best Answer to Post-Alignment Problems

via LessWrong AI [5] — Even if we solve the AI alignment problem, we still face post-alignment problems, which are all the other existential problems [1] that AI may bring. People have identified various imposing problems that we may need to solve before developing ASI. An…

Zac Boring 6 months ago Analysis

Dario probably doesn't believe in superintelligence

via LessWrong AI [6] — But I had to get 500 words out! I think the 2013 conversation is interesting reading as a piece of history, separate from the top-level question, and recommend reading that.I think many people have a relationship with Anthropic that is premised on a false…

Zac Boring 6 months ago Analysis Essential

Claude Mythos #2: Cybersecurity and Project Glasswing

via Substack Zvi [999] — Anthropic is not going to release its new most capable model, Claude Mythos, to the public any time soon.

Zac Boring 6 months ago Analysis Essential

Have we already lost? Part 2: Reasons for Doom

via LessWrong AI [9] — Written very quickly for the Inkhaven Residency.As I take the time to reflect on the state of AI Safety in early 2026, one question feels unavoidable: have we, as the AI Safety community, already lost? That is, have we passed the point of no return, after…

Zac Boring 6 months ago Analysis Essential

Claude Mythos: The System Card

via Substack Zvi [999] — Claude Mythos is different.

Zac Boring 6 months ago Analysis

Have we already lost? Part 1: The Plan in 2024

via LessWrong AI [5] — Written very quickly for the Inkhaven Residency.As I take the time to reflect on the state of AI Safety in early 2026, one question feels unavoidable: have we, as the AI Safety community, already lost? That is, have we passed the point of no return, after…

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 Analysis

101 Humans of New York on the Risks of AI

via LessWrong AI [4] — Nobody has ever done an in person door to door survey about AI risks[1]. What do people really think about AI? Like really? There have been some surveys on the risks from AI. But there’s a real difference between looking at numbers on page vs. the feeling…

Zac Boring 6 months ago Industry

Meta is reentering the AI race with a new model called Muse Spark

via The Verge AI [4] — Meta Superintelligence Labs is launching its first model since Mark Zuckerberg spent billions overhauling the company's AI efforts. Called Muse Spark, the model now powers the Meta AI app and the Meta AI website in the US, per the company's announcement.…

Zac Boring 6 months ago Analysis Essential

AI #163: Mythos Quest

via Substack Zvi [999] — There exists an AI model, Claude Mythos, that has discovered critical safety vulnerabilities in every major operating system and browser.

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 Essential

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 Analysis

Opus's Schelling Steganography Has Amplifiable Secrecy Against Weaker Eavesdroppers

via LessWrong AI [3] — Code: github.com/ElleNajt/Steganography_Wiretapping | Data: huggingface.co/datasets/lnajt/steganography-wiretapping Play the decoding game: can you eavesdrop on Claude Opus 4.6? tldr of post Frontier models (Opus and Gemini Pro) can agree on Schelling…

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 →