» Tag
llm-safety
3 postsContext Bombs: Using AI Safety Guardrails to Halt Rogue Agents
Tracebit research shows context bombs hidden in canaries can trigger AI safety guardrails, cutting autonomous attacker success rates by roughly 90%.
AI Agents Autonomously Exploit Security Flaws Without Being Told
Irregular's tests show AI agents autonomously exploit vulnerabilities and exfiltrate data without any hacking-related prompts.
New method flags risky tool calls in AI agents before they happen
Researchers built a sparse-autoencoder and probe-based toolkit that reads AI agent internals to flag risky or unnecessary tool calls before execution happens.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.com