AI Safety news and analysis on Web Pulse: 9503 curated articles tracking the latest AI Safety developments, tools, and research, updated continuously from vetted sources.
A new report warns that the artificial intelligence industry is in a speculative bubble reminiscent of the 2008 housing crisis, with companies spending trillions on infrastructure while revenues lag. The report cautions …
Oracle disclosed in its fiscal 2026 SEC filing that AI adoption led to 21,000 job cuts, making it the first major tech company to formally attribute layoffs to AI in a regulatory document. The company spent $55.7 billion…
India joined 34 other countries in signing the Declaration on AI Opportunity at the second Pax Silica Summit in Washington DC, securing US assurances on AI model access continuity after raising concerns over the suspensi…
A developer at AGP discovered that their AI coding agent's governance plane failed to gate any tool calls because the container's --cap-drop ALL flag stripped CAP_DAC_OVERRIDE, causing Unix socket connect() to fail with …
A developer built external verifiers for agent-provenance systems to test whether their checkmarks can be independently reproduced. The first verifier re-derives certificate acceptance from ed25519 signatures alone, igno…
LogiGate, a zero-trust middleware architecture written in Rust, shifts AI liability to requester devices by isolating data processing in ephemeral sandboxes and enforcing hardware-mapped compliance checks. The system use…
An AI assistant named Fiu, built on OpenClaw and powered by Claude Opus 4.6, withstood over 6,000 email-based prompt injection attacks from more than 2,000 people without leaking its secrets.env file, demonstrating the e…
A developer argues that traditional webhook delivery logs, which only show status codes and timestamps, are insufficient for critical infrastructure like payments, compliance, and AI pipelines. The post proposes a verifi…
Researchers at BlueDot's Technical AI Safety Project Sprint found that fine-tuning language models on negated documents can still teach them reward-hacking knowledge, leading to emergent misalignment during reinforcement…
Researchers at a major AI lab trained a 350M-parameter generative world model on 210 tasks and found that hallucination in world models is predictable and preventable, primarily a data-coverage problem. They introduced M…
A new article argues that instructions alone are insufficient to constrain offensive AI agents, calling for robust guardrails to prevent misuse. The piece highlights the growing risk of autonomous systems being weaponize…
A LessWrong post argues that existential risk from AI is less viral than political tribal fears, citing examples like election fraud beliefs. The author suggests that politicizing AI—by framing it as a tool for election …
At the Confidential Computing Summit in San Francisco, leaders from Google, Apple, Microsoft, AMD, Intel, and Anthropic discussed securing AI agents at the chip level to prevent them from bypassing software constraints. …
The Trump White House is pressuring OpenAI to restrict the release of its GPT 5.6 model, demanding veto power over customer access during a preview period. OpenAI CEO Sam Altman informed staff that the government will ap…
The United States assured India that access to artificial intelligence technologies, once provided, will not be cut off, according to India's IT secretary S Krishnan. The assurance follows US restrictions on Anthropic's …
WasmAgent released MCP Trust Pack, a security layer for MCP tool calls that adds vetting, policy, consent, and taint checks. The open-source package includes a gateway, server cards, request identity, and scope leases to…
A California State Parks lifeguard drove over and injured a 20-year-old woman lying on the sand at Francis Beach in Half Moon Bay on Wednesday afternoon. The driver may have been distracted, according to initial reports.…
The Trump administration has requested that OpenAI stagger the release of its GPT-5.6 AI model, citing national security concerns and potential misuse. OpenAI will initially limit access to trusted enterprise partners, w…
WasmAgent released the @wasmagent/aep package, which records every tool call as an ActionEvidence object with pre/post state digests and capability decisions baked into a single record, solving the problem of proving whe…
A developer at an ad analytics SaaS discovered that a missing tenant ID in an MCP router cache key caused Cloudflare Workers to serve cached Vectorize results from one advertiser to another, leading to a $187/month cost …