Model Releases
Great prompt from Anthropic. It helps steer long runs when using Opus 5.5 in Claude Code. Apparently, on long-running tasks, the model somet…
Great prompt from Anthropic. It helps steer long runs when using Opus 5.5 in Claude Code. Apparently, on long-running tasks, the model sometimes stops to report instead of continuing. I've noticed tha
Great prompt from Anthropic. It helps steer long runs when using Opus 5.5 in Claude Code. Apparently, on long-running tasks, the model sometimes stops to report instead of continuing. I've noticed that this happens a lot with frontier models.
Related
- Sonnet 5 is here! This is going to support better long-running agents. Previous Sonnet models were unreliable, so it's great to see the impr…
- The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents
- Interesting new approach to enable memory in long-running agents. Weighted Memory Tree organizes execution into tasks, subtasks, and actions…
Source: DAIR.AI (X) | 2026-09-22