OpenAI trained GPT-Red, an internal-only attacker model, using self-play reinforcement learning against a population of defender LLMs. It beat human red-teamers 84% to 13% on a replicated indirect ...
Curated directory of Rust-based libraries and crates for AI model training, inference, agentic systems, and related tools. Include popular crates like candle, burn, dfdx, tract, and more. Focus on ...