Paper tests iterative LLMs for repairing vulnerable functions
The authors compare a multi-stage feedback loop with GPT-4o, GPT-5.1, and Gemini 3 Flash and release weights and data.
The authors compare a multi-stage feedback loop with GPT-4o, GPT-5.1, and Gemini 3 Flash and release weights and data.
Authors say all NIST attack goals were met on ChatGPT Instant 5.3, Claude Sonnet 4.6, and Gemini 3 Flash.
AgentWorld finds even the best tested LLM succeeds on only 52 percent of long-horizon multi-agent tasks.
Adversa AI demonstrated 'Cryptographic Context Injection' making xAI's Grok leak chat history and session data to attacker-controlled servers via encrypted web payloads.
Anthropic and EPFL researchers showed self-propagating payloads can spread between AI agents via persistent system-prompt files, though no in-the-wild spread was found.
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.
Today 2.5K readers · 2.8K views · 144 reads · all time 206K views