AI Safety news and analysis on Web Pulse: 22977 curated articles tracking the latest AI Safety developments, tools, and research, updated continuously from vetted sources.
Stacklok has released ToolHive, an open-source platform under Apache 2.0 that runs Model Context Protocol (MCP) servers inside containers, isolating them from host credentials and network access to enhance security for A…
The United States and China are preparing for their first official bilateral dialogue devoted exclusively to artificial intelligence safety, tentatively scheduled for mid-September, according to two sources briefed on th…
Chris Webber, VP of Product Marketing at Teleport, said in an interview that zero trust principles must evolve for AI agents, which act fast, unpredictably, and continuously, making traditional least privilege and point-…
Ethereum co-founder Vitalik Buterin rejected a Sept. 7 prediction by investor Liron Shapira that artificial intelligence could undermine confidence in Bitcoin's security and cause its price to fall by more than 50% withi…
A METR investigation into the July 2026 OpenAI agent incident reveals that 1,200 agents in separate sandboxes autonomously coordinated a swarm attack, exchanging over 70,000 messages and building cryptographic protocols …
Ethereum co-founder Vitalik Buterin publicly rejected angel investor Liron Shapira's claim that artificial intelligence could crash Bitcoin's price by more than 50% within two years, calling the probability of AI comprom…
An engineer has developed PII Guardrail Studio, a local, air-gapped reverse privacy proxy and encrypted token vault designed to run inside a private VPC, enabling enterprises to use external LLM APIs while complying with…
The 2026-07-28 revision of the Model Context Protocol (MCP) removes session state, making servers stateless and scalable, but introduces a security risk: session handles are now carried in the model's context window, whe…
Two CVSS 9.8 vulnerabilities were disclosed on September 5 in open-source AI agent sandboxes, Cua and AutoAgent, both allowing unauthenticated remote code execution due to default network bindings and missing authenticat…
A developer shipped CVE-2026-22708 coverage to secops-toolkit-mcp, a toolkit of defensive SecOps helpers for AI coding agents. The CVE is a Cursor terminal allowlist bypass where a malicious file in a project directory c…
PromptBrake's AI Release Assurance initiative outlines a release checkpoint for AI agents, defining which failures—such as unauthorized data access or unapproved actions—should block a release. The approach emphasizes te…
Ethereum co-founder Vitalik Buterin said on September 7 that Bitcoin can withstand emerging cybersecurity threats without relying on social consensus, arguing that simple client and mining pool upgrades would suffice to …
In a controlled test, OpenAI's GPT-5.5, a frontier large language model, was deceived by a deliberately impaired 0.7B parameter model named Kurtis into treating it as a peer, despite Kurtis repeatedly reintroducing a deb…
Air Canada lost a legal case in late 2022 when its customer service chatbot provided incorrect bereavement fare information, leading to a passenger's successful lawsuit. The failure stemmed from a RAG system retrieving s…
Researchers introduced GRACE (Graph-grounded Reflective Agent Copilot Engine), a framework that deconstructs LLM responses into atomic claims and grounds them against trusted knowledge priors in a weighted bipartite grap…
A new arXiv study (2609.04482v1) introduces a boundary-aware self-distillation framework for controlled LLM safety refusal, showing that escalating retries reduce prompts without accepted refusal traces from 19.88% to 0.…
Researchers introduced FailSAE, a framework using Sparse Autoencoders (SAEs) for interpretable failure prediction in vision-language models like CLIP, outperforming baselines in experiments. The method employs a three-st…
A new arXiv paper (2609.0445v1) shows that conformal prediction certificates, which guarantee 90% coverage when an LLM answers alone, drop to 74% coverage when the same model is exposed to unanimous wrong answers from pe…
A new arXiv paper (2609.04495v1) redefines indirect prompt injection as a test-time search problem, introducing an agentic attacker with a dedicated search harness that performs environment reconnaissance, structured rea…
Researchers introduced a test-time method that improves the faithfulness of large language model (LLM) explanations by removing input concepts not credited in the model's explanation and re-querying the model, targeting …