A new policy gate for AI agents adds three security layers—path scoping, a shell denylist, and an SSRF guard—to block dangerous tool calls before they reach execution, according to the latest installm…
HuggingFace suffered an AI-assisted cyberattack last week and was unable to analyze it using frontier models from Anthropic or OpenAI because those models' safety guardrails blocked cybersecurity-rela…
A new installment of the 'Build a Basic AI Agent From Scratch' series introduces Docker sandboxing, prompt-injection defenses, and schema validation to close security gaps left by human-in-the-loop co…
A developer built a basic AI agent from scratch with human-in-the-loop controls and security features, adding permission modes that require user approval for risky actions like writing files or runnin…
Anthropic suspended access to its Claude Fable 5 and Mythos 5 models after the US Commerce Department ordered it to do so, citing a third-party report of a jailbreak method that bypassed safeguards. T…
Anthropic released its most capable AI model, Claude Fable 5, after previously hiding it due to safety concerns. The company also released Mythos 5, identical to Fable 5 but with a safeguard that degr…
A developer building a basic AI agent from scratch adds long task planning capabilities by implementing an in-memory scratchpad and to-do list, enabling the agent to decompose complex tasks and track …
A developer published a tutorial on building a basic AI agent from scratch, adding tool-calling capabilities such as bash execution, file reading, and glob file searching. The tutorial builds on a pre…