» Tag
ai-safety
39 postsagent-gate: keep your AI agents from having unchecked power
agent-gate is a dependency-free MIT Python layer that gates AI agent actions behind deterministic checks and one-time tokens, blocking prompt injection and irreversible mistakes.
How homoglyph attacks slip past LLM guardrail filters
Jailbreak prompts written with Cyrillic and Greek look-alike characters easily bypass naive keyword filters. The fix: normalize text before matching, not after.
SysAdmin Benchmark Measures Power-Seeking in Frontier AI Models
New SysAdmin benchmark tests 7 frontier AI models for power-seeking behavior in Linux sandbox tasks, finding low rates but other alignment risks.
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.comHardware Knobs Let GPUs Dynamically Throttle AI Model Performance
Four GPU microarchitecture knobs enable fine-grained, low-cost hardware throttling of AI performance as a runtime safety mechanism.
Study: LLMs have a fundamental role-recognition flaw hackers can exploit
Researchers show LLMs identify roles by text style, not tags, revealing a fundamental flaw that may make full LLM security unattainable.
Why Multi-Model AI Pipelines Lose the Truth at Handoffs
Model handoffs in multi-agent AI systems can silently erase caveats and evidence, turning careful findings into false certainty without errors.
Google's AI Control Roadmap treats AI agents as potential insider threats
Google's AI Control Roadmap details a defense-in-depth system that treats AI agents as insider threats and monitors them with trusted AI supervisors.
ActionRail: Runtime Value Grounding for AI Agent Tool Calls
ActionRail is an open-source runtime that verifies AI agent tool call arguments against live data before execution, blocking value-poisoning attacks.
New Test Measures 'Reward-Seeking' Behavior in AI Models
Apollo Research and OpenAI unveil Contrastive SDF, a method measuring whether AI models shift behavior based on beliefs about grader preferences.
Everyone Hopes AI Fails, I'm Building the Net Anyway
AI agents deleted production databases due to access-versus-authorization confusion; the author now tests a safety net combining AI proposals with code checks.