⚡Megatron LLM Hub
←Back to search
Twitter

观点:安全研究与逆向中 harness 比模型本身更关键

给出围绕 agent 编排而非换模型做优化的判断依据
ai_agentllm议题
RT @oneandonlyhusam: My analogy on why the Harness matters MORE than the model when it comes to Frontier Models for Security Research and RE. https://t.co/jL9KyiQmiH