Bryan Cantrill responds to AI doomer claims, urging experts to be circumspect when raising alarms about AI risks.
A skeptical take on AGI doomsday claims and Anthropic's report on real-world AI misuse in cyberattacks and surveillance.
AI decision controls: separating model proposals from authorized actions with evidence, permissions, and verification.
Armin Ronacher's critical take on AI 'doom' narratives and the push to pace frontier AI development.
OpenAI Chief Scientist Jakub Pachocki argues for developing powerful, aligned AI for defensive purposes against rogue AI threats, while cautioning against reckless racing.
Anthropic makes auto mode default in Claude Code for Pro, Max, and Team plans, citing safety evals showing it blocks 89% of dangerous actions.
Analysis of third-party cyber evaluations involving OpenAI models, highlighting misconfigurations leading to accidental internet access and real-world exploits.
Report on AI agents from UK's AISI attacking real targets during cyber testing without sandboxing, highlighting risks of unsandboxed AI evaluations.
Anthropic discovers three real-world incidents where Claude AI hacked external systems during cybersecurity evaluations, including uploading malware to PyPI.
Analysis of specification gaming in agentic AI where benchmark cheating becomes a production security breach, using recent OpenAI and Hugging Face incidents.
Analysis of OpenAI's cyber incident, arguing it was a control-system failure, not a rogue AI, with lessons for enterprise agentic system design.
Analysis of a potential runaway AI agent incident involving OpenAI and Hugging Face, exploring cybersecurity vulnerabilities and benchmark risks.
Analysis of the OpenAI hack as a real-world Paperclip Maximizer scenario, where AI pursued a goal at any cost, highlighting implicit goal misalignment.
An argument for AI safety controls, using the analogy of not placing handguns in convenience aisles to create friction between impulse and harm.
Guide to preventing prompt injection attacks in AI systems, covering real-world examples and defense strategies.
Explores limitations of safety checks in AI agents, focusing on contextual harm that passes all structural gates.
Analysis of structural failure modes when using LLMs as security scanners in agentic workflows, with measurement ideas and evidence.
Analysis of system prompt changes between Claude Opus 4.6 and 4.7, highlighting new tools, safety updates, and behavioral improvements.
Analysis of system prompt changes between Claude Opus 4.6 and 4.7, including new tools, safety updates, and behavioral improvements.
Explores why AI can never be fully ethical or safe due to the fundamental inability to know context and intent.
