Opus 4.8+GPT-5.5分工跑长任务
Omar Sanseviero分享运行自主长时编码智能体的经验，建议用Opus 4.8做规划、GPT-5.5执行，并用Deepseek、Qwen、Kimi或MiniMax等模型作为评估器。他强调多模态目标比纯文本目标更强，能帮助智能体保持方向。清晰定义目标、消除模型假设、避免奖励黑客行为是关键。
How to effectively run autonomous long-running coding agents? This is one of the most exciting disc...
How to effectively run autonomous long-running coding agents? This is one of the most exciting discussions on agents I've ever had. I recorded it and am making it freely available. (bookmark it) The idea of autonomous long-running agents is a real thing. We talk about lots of things like /goal, /loop, and dynamic workflows, and what comes next. One interesting discussion was around how to make the agent run for longer while ensuring it stays on track. Most models today will struggle to coordinate work effectively. They sometimes pause the work early. Lots of mistakes happen, and lots of weird shortcuts (reward hacking). What helps is to be extremely clear about the goals it needs to achieve. To clarify the dos and don'ts clearly. Eliminate any assumptions you think the model would make. Deep expertise matters so much in this. But you can get far through careful planning. My formula currently is to use Opus 4.8 for planning carefully and GPT-5.5 for all executions. For the evaluator (via /goal), I am often using something like Deepseek or the latest models from Qwen, Kimi, and MiniMax, etc. Another insight we discussed to enforce goals is to provide strong visual cues for the agent to compare with. I found that a multimodal goal is a much stronger goal than a plain text one. And use agents to help you set clear goals. Watch here: academy.dair.ai/events/cmplo7v… 💬 6 🔄 0 ❤️ 9 👀 425 📊 7 ⚡