catch
9 stories and discussions about catch, aggregated from every source we track.
🛡️ Regex catches 0%, Meta's Prompt Guard 2 catches 1% of 629 realistic AgentDojo injection attacks when they're buried in tool output. Reproducible benchmark. - rudratoshs/buried-injections
A linter for rules a normal linter can't check. (powered by Typesafe) - darkmatter/adhere
216 passing tests. A feature that was completely broken. Here is the gap between those two facts, and...
On real multi-year Comcast support traffic, a fine-tuned verifier's gray-zone positive rate drifted 5x and the model went from helping to actively hurting. Here's the failure, and the three-detector monitor we built…
We found a clear internal signal in models that accompanies reward hacking, and built probes that detect it — enabling efficient, real-time detection of reward hacking at scale.
Detect structural and semantic OpenAPI compatibility risks
I wanted to know one thing. When an AI model reads a data-science tutorial, does it check the code or...
OpenAI popularized the modern generative AI chatbot, but as its 2026 DevDay event approaches, it's fallen behind in one of the industry's hottest categories: continuously running, consumer-facing AI agents. On Tuesday, it will likely try to capture the lead in that race. Rumors abound that OpenAI will release its own AI agent, dubbed Aeon - its answer to Meta's Muse, SpaceX's Grok Bot, OpenClaw, and many more. Aeon could have a shot at success, but to beat the competition, it would need to pull together the best features of several different agent platforms. The ideal system would be as useful as the open-source OpenClaw, as cheap and easy … Read the full story at The Verge.