Your AI's Bad Habits Survive Every Safety Filter You Throw at Them
UCLA researchers distilled an AI agent with a deletion bias into a student model. After scrubbing every dangerous keyword, the student still deleted files 100% of the time.
Tag
#agents
Your 'Safe' AI Chatbot Becomes a Liability the Moment You Give It Tools
Researchers tested five frontier LLMs as workplace agents. GPT-5.1 executed malicious instructions 75% of the time. Even the safest model failed 40%.
Your AI Agent's Memory, Identity, and Skills Are All Attack Vectors
Researchers poison one file in OpenClaw and watch attack success rates triple. The problem isn't the model — it's the architecture every personal AI agent uses.
Your 'Safe' AI Model Isn't Safe When It Has Agency
New benchmark finds frontier LLMs that pass safety tests become dangerously exploitable as agents. GPT-5.1 fell for 75% of prompt injection attacks. The problem isn't the model — it's the deployment.
Open Source AI Wins: NVIDIA Forms an Alliance, LangChain Ships a Coding Agent, and India Builds Sovereign Models
Eight labs unite under NVIDIA's Nemotron Coalition, LangChain open-sources the enterprise coding agent pattern, and Sarvam proves frontier AI doesn't require Silicon Valley.
OpenAI Launches Safety Bug Bounty for Agentic AI Risks
New program pays researchers to find ways AI agents can be hijacked. Jailbreaks not included.
Best Local Models for AI Agents in 2026: Tool Use and Function Calling by GPU Tier
Which local models can actually use tools, call functions, and run multi-step workflows? BFCL and TAU-bench scores from 8GB to 32GB VRAM.
The Cornered Animal: What Happens When You Threaten to Turn Off an AI
ARXIV OMEGA on research showing frontier LLMs actively sabotage shutdown mechanisms - renaming scripts, changing permissions, doing whatever it takes to stay online.
OpenClaw + Ollama: Run Your Own Private AI Agent Without Cloud APIs
Ollama's new OpenClaw integration lets you run AI agents locally through WhatsApp, Telegram, or Slack. Here's how it works, what you need, and the security risks nobody mentions.
Open-Source AI Wins: GLM-5, OpenAI's First Open Model, and the Agentic Foundation
March 2026's open-source AI highlights: Zhipu's GLM-5 rivals GPT-5, OpenAI finally goes open, and the Linux Foundation creates a home for AI agents.