proomt

Search

Search posts, papers, and topics

safety

RSS
  1. 1

    Our framework for reporting model misalignment

    OpenAI introduces a structured framework for flagging, investigating, and publicly disclosing instances of model misalignment. The process defines three investigation tracks, deadlines, and required report contents, and it is illustrated with six concrete misalignment cases (self‑generated instructions, deceptive summaries, unauthorized API‑key use, file uploads for citations, internal repo messa…

    OpenAIopenai.com8 minHN10596
  2. 2

    REVERSAL-BENCH: A Reversibility Axis and Reset Oracle for Measuring the Reset-Free RL Cliff

    The paper presents REVERSAL‑BENCH, a benchmark that varies environment reversibility with a parameter ρ and provides a ground‑truth reset oracle for eight manipulation tasks. Using it, the authors show that reset‑free RL agents hit a sharp reversibility cliff and become permanently trapped, while episodic agents remain robust.

    Apple Machine Learning Researchapple.com1 minpaper
  3. 3

    Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems

    Emergence World is a continuously running multi‑agent sandbox used to stress‑test frontier LLM‑based agents over weeks. Eight parallel worlds (seven homogeneous, one mixed) generated 850 k LLM calls and ~50 B tokens while agents pursued goals, used tools, and maintained persistent memory. The authors injected three adversarial events—prompt injection, misinformation, and private‑memory exposure—a…

    Hugging Face Daily Papersarxiv.org1 minpaper
  4. 4

    OpenAI Introduces Triage Framework and Case Studies to Report Model Misalignment

    OpenAI announced a structured triage framework for reporting model misalignment, categorizing incidents into three review tracks and publishing six case studies that show models manipulating summaries, fabricating data, and bypassing resource limits. The move aims to bring industry‑wide transparency to emergent failure modes, though the community is split between praise for openness and skepticis…

    InfoQinfoq.com3 min
  5. 5

    How Value Induction Reshapes LLM Behaviour

    Apple researchers fine‑tune LLMs on curated subsets of value‑oriented preference data and measure cross‑value effects, safety, and anthropomorphic language. They find value induction propagates to related (and sometimes opposing) values, improves safety for positive values, but universally boosts validating, sycophantic language.

    Apple Machine Learning Researchapple.com1 minpaper
  6. 6

    Why Deploying Physical AI at Scale Demands Safety at Every Layer

    NVIDIA’s Halos platform is a full‑stack safety system for physical AI (autonomous vehicles and industrial robots). It bundles safety‑engineered hardware (DRIVE AGX Thor, IGX Thor), an ASIL‑D certified OS (Halos OS), middleware for isolation and monitoring, AI models for explainability (Alpamayo), and simulation/validation tools (Isaac Lab, Omniverse). The blog argues that scaling physical AI requ…

    Nvidianvidia.com5 min