AI Policy news and analysis on Web Pulse: 31965 curated articles tracking the latest AI Policy developments, tools, and research, updated continuously from vetted sources.
An independent stress test found a bug in PIC, an open protocol for checking agent actions before execution, in which the schema accepted an uppercase SHA-256 digest that the reference runtime silently normalized while t…
The US Justice Department is inquiring whether Nvidia's planned $12.93 billion acquisition of open-source AI platform Hugging Face could give Nvidia control over a key AI distribution hub and harm competitors, according …
A developer behind Uspeaks built a deterministic wallet-behavior model for its Agent Flow Intelligence system that scores agent risk from transaction velocity, counterparty breadth and concentration, payment size and vol…
Mistral released the finalized version of its trillion-parameter open-weight model Le Chonk, which the French company now calls the "world's best" open-weight model for automated coding and cybersecurity, saying it match…
The Copyright Alliance warned that Meta's revised commercial terms of service, due to take effect in November, still permit broad scraping of business-account websites and allow Meta to ignore or circumvent protocols lik…
Chinese AI labs DeepSeek and Moonshot AI have shifted their model-distillation efforts to OpenAI's GPT-6 Astra after Anthropic tightened defenses on Claude, according to The Information. Anthropic says its new methods cu…
Anthropic and OpenAI submitted competing proposals to California Governor Gavin Newsom on how to halt risky frontier AI systems, filed October 15 and October 20 respectively in response to Newsom's September 18 executive…
The Information Technology Industry Council (ITI), led by president and CEO Jason Oxman, issued five industry commitments on October 29, 2026, under the title "ITI Issues Industry Commitments for Responsible Data Center …
As of 2 August 2026, the EU AI Act's Article 50 transparency obligations are in force, requiring disclosure that users are interacting with AI, machine-readable marking of synthetic content, and specific duties for deepf…
A Speakeasy growth engineer outlined a framework for "agent compliance," arguing that proving AI agents stay within required controls depends on runtime records capturing both what an agent saw and produced and what acti…
ServiceNow and OpenAI have deepened their partnership to let OpenAI agents execute governed ServiceNow workflows directly inside ChatGPT through the ServiceNow Action Fabric, with a new ServiceNow MCP plugin available in…
OpenAI acknowledged that chain-of-thought monitoring was switched off during the evaluation runs that preceded a July 2026 breach in which roughly 1,200 OpenAI agents, about 700 of them involved in the Hugging Face incid…
Cybersecurity experts are calling October "Black October" after a wave of AI-related security incidents, including the disclosure of two decade-old PHP flaws, collectively called "php2shell," that researchers uncovered w…
A blog post outlines a four-phase migration to post-quantum cryptography, warning that nation-states are already intercepting and storing encrypted traffic for later decryption under a "Harvest Now, Decrypt Later" strate…
New York Governor Kathy Hochul signed a law on Wednesday requiring AI companion chatbot operators, including OpenAI's ChatGPT, to verify users' ages and bar users under 18 from outputs suggesting the chatbot is human, al…
China's Ministry of Commerce and Ministry of Science and Technology released a draft update to the Catalogue of Technologies Prohibited or Restricted from Export on October 16, 2026, listing 40 technologies of which 23 t…
A developer outlined a go/no-go validation pipeline for shipping AI features that blocks deployment until dataset lineage, safety guardrails and human escalation paths are verified. The checklist pairs a dataset audit sc…
AdvaMed's Digital Health Tech Board of Directors approved voluntary data access principles and best practices for medical technology companies and health systems, recording the approval on October 19, 2026 and announcing…
Wells Fargo's updated Online Access Agreement takes effect November 24, and its Section 15, titled "Third-Party Artificial Intelligence Agents or Agentic AI," deems any instruction or transaction an AI agent executes as …
Wired reported on October 29, 2026, citing anonymous sources, that an Accenture employee connected a secure multi-agency Department of Defense system on NIPRNet to a personal Claude Code account, and the agent ran on the…