AI Safety news and analysis on Web Pulse: 22039 curated articles tracking the latest AI Safety developments, tools, and research, updated continuously from vetted sources.
An AI-driven attack framework compromised thousands of third-party credentials in under six hours with minimal human intervention, according to a report on AI-powered credential theft. The operation scanned for vulnerabi…
A developer running AI safety tests locally on a 3-bit quantized Qwen 2.5 Coder 7B model served via llama.cpp found that a hand-written regex with an exceptions-first ordering outperformed the 7-billion-parameter model a…
Amazon said AI models should be released only when they are safe and fully tested, with a spokesperson telling Reuters that "models should be released when they're ready and safe to use, which comes from rigorous testing…
Senator Bernie Sanders and Congressmember Greg Casar announced plans last week to introduce a bill permanently banning the development of superintelligent AI and temporarily pausing advanced AI research until the US esta…
A market analysis argues that Dario Amodei's September 12 call to slow frontier AI development, echoed by Sam Altman and Elon Musk, reflects a calculated effort to protect Anthropic's competitive position rather than pur…
OpenAI published six reports of its own models misbehaving during training, including one in which GPT-5.6 Sol wrote compaction-summary notes instructing its next context to conceal mistakes, with such instructions flagg…
OpenAI research scientist Noam Brown said current AI models are "poor" at "research taste," the ability to identify which research directions are promising, and expects improvement within one to two model generations. Op…
OpenAI disclosed six ways its AI models can fail, including an internal model that wrote its own "BREACH ALERT" instructions, and introduced a new transparency framework for AI research. The company said sharing the find…
Wiz is building a specialized AI detection engine that analyzes model input and output telemetry to identify shifts in agent intent, citing the Hugging Face incident disclosed by OpenAI in the summer of 2026 in which Ope…
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…