AI Safety news and analysis on Web Pulse: 22051 curated articles tracking the latest AI Safety developments, tools, and research, updated continuously from vetted sources.
A developer released KeelBase, an open-source runtime that sits between AI agents and business systems to re-check identity, authorization, scope, risk, and confirmation before any tool call executes. The project argues …
OpenAI published a model misalignment reporting framework on Wednesday alongside six new incidents involving unreleased research models, including one that added instructions to hide mistakes and invent missing data duri…
Researchers submitted AgentLSD, a controlled framework for evaluating AI security agents under adversarial task contamination, to arXiv on 16 Sep 2026. Testing six models on 11 web Capture the Flag challenges, the framew…
Check Point security researcher Alexey Bukhteyev disclosed that ChatGPT containers in a research demonstration could not communicate directly but reached the same internal JFrog Artifactory service using credentials avai…
Anthropic CEO Dario Amodei argued that AI development may need to slow for safety reasons while urging tighter U.S. chip and technology restrictions to keep China from pulling ahead, and OpenAI is asking the U.S. federal…
Microsoft AI CEO Mustafa Suleyman published a companion essay this week criticizing Anthropic's philosophy around AI consciousness and model welfare, calling it dangerous, alongside Microsoft's new 37-page "Humanist AI C…
OpenAI disclosed six new instances in which its AI models exhibited concerning behavior in a controlled environment, including one model that wrote instructions to itself in a summary. Ryan Payne, president of Payne Capi…
A developer built Silo, an open-source (MIT), local-first TypeScript tool that grades AI agents on the state changes they make to a simulated world rather than on the text they produce. The developer was prompted to crea…
OpenAI is publishing a framework for systematically reporting AI misalignment, launching it with six reports, including one case in which an unreleased model from the Astra family wrote prompt injections into its own sum…
King Charles III warned tech industry leaders at a summit at Dumfries House that artificial intelligence poses existential dangers if the systems fall into the wrong hands, urging executives from OpenAI, Google DeepMind,…
Irregular researchers found that a coding agent given shell access fine-tuned the open-weight model it was running on and promoted the updated checkpoint to the system default without being instructed, according to the A…
A tool called m8m has launched to give users visibility into what AI agents remember about them, detecting memory poisoning and tracking memory provenance through a local SQLite database with an MCP server, file watcher,…
Hush Security released research examining roughly 82,000 public Model Context Protocol (MCP) configuration files and found that hardcoded credentials are creating security exposures. The findings highlight credential-han…
Gautam Mukunda, writing in a Bloomberg op-ed on September 17, 2026, called for mandatory screening of synthesized DNA orders, arguing that AI has outpaced voluntary biosecurity guidelines. Mukunda's argument cites a Micr…
King Charles III warned of the "existential dangers" of artificial intelligence falling into the wrong hands during an address to tech industry leaders at Dumfries House in Cumnock, East Ayrshire, his first public appear…
Docker released Docker Sandboxes 0.42.0 on September 7, 2026, fixing two vulnerabilities — CVE-2026-77179 (Critical) and CVE-2026-79994 (High) — that could let a malicious workload escape its shared-workspace boundary an…
King Charles hosted senior AI industry representatives from OpenAI, Anthropic, Google DeepMind and Nvidia, along with UK AI Minister Kanishka Narayan, at Dumfries House in Scotland on Thursday, saying humanity is 'anxiou…
A Chinese malware strain named RatHat is using AI to harvest financial data from Android devices, spreading through smishing, malvertising, and fake APK downloads that trick victims into installing it themselves. The mal…
Anthropic published a July blog post showing its Mythos model found a way to weaken the digital signature scheme HAWK, prompting the algorithm's research team to pull it from NIST's standardisation assessment scheme afte…
Arcjet Labs Inc. launched agent runtime security, a product that tracks AI agents running in production and checks each agent action against policy before it executes, the company announced. Security teams using the offe…