Heidelberg AI News
All stories
3 stories about Claude Opus 5.5
Saturday 31 October
- MarkTechPost
ArticleMarkTechPost
Meet Factory Droid 1.0: A Model-Independent Coding Agent Harness Built on Script Mode
Factory released Droid 1.0, a model-independent coding agent harness that makes programmatic tool calling the default. On Factory’s own Terminal-Bench 4 runs, Droid scores 65.2% with Claude Opus 5.5 at $4.73 per passed task.
Tuesday 27 October
- Latent Space
ArticleLatent Space
How Anthropic ships Claude with Claude: Separating the Brain from the Hands
In a Latent Space episode, Anthropic's heads of engineering (Katelyn Lesse) and product (Angela Jiang) discuss the launch of Claude Opus 5.5, which has held the top-ranked LLM title for about a month, and the engineering behind the Claude Platform. The episode covers how Opus 5.5 is cheaper to run than its predecessor, changes to API integration including preserving thinking blocks across turns to protect reasoning against distillation, and how early access programs run evaluations in customers' own harnesses to see the model on tasks Anthropic's own products do not cover. A central mental model is separating an agent's 'brain' (session log and harness) from its 'hands' (the sandbox that executes code), which improves latency and reliability and adds security by keeping credentials out of the sandbox. The episode also covers Managed Agents' memory feature ('dreaming'), a roadmap that has shifted more attention toward safety, and the practice of evaluating agents.
ArticleLatent Space
How Anthropic ships the #1 LLM in the World safely: Separating the Brain from the Hands
In this Latent Space episode, Katelyn Lesse and Angela Jiang explain the engineering behind the Claude Platform, covering the launch of Opus 5.5, separating the model's 'brain' from the agent's 'hands,' scaling APIs, and building reliable managed agents.