Understand this story
On October 28, 2026, Anthropic engineering lead Katelyn Lesse and product lead Angela Jiang gave an interview on the Latent Space podcast, discussing the release of Opus 5.5. The interview covered adjustments to the model's writing style, pricing per dollar of intelligence, and API changes such as requiring thinking blocks to be retained across turns to prevent distillation. The two also described how Claude Managed Agents separate conversations and the harness from the sandbox that executes code, mount credentials separately through a proxy, and ensure that a sandbox failure does not take down the entire conversation, and explained that Dreaming is implemented as one managed agent inspecting another agent's history and writing back to memory. The team said that as safety work for model releases has grown heavier, recent efforts have shifted more toward safety, with progress on features such as skills and memory slowing relatively.
AI-generated from public reports
Latest development · Report
Anthropic's Engineering and Product Leads Discuss the Opus 5.5 Release and Claude's Agent ArchitectureDevelopments
1 confirmed developments
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 28
Latent SpaceSelected
Anthropic's Engineering and Product Leads Discuss the Opus 5.5 Release and Claude's Agent Architecture
In a Latent Space podcast interview, Anthropic engineering lead Katelyn Lesse and product lead Angela Jiang discussed the Opus 5.5 release, covering adjustments to the model's writing style, pricing based on intelligence per dollar, and API changes such as requiring thinking blocks to be retained across turns to prevent distillation. The interview also described Claude Managed Agents' approach of separating sessions and the harness from the sandbox that executes code, with credentials mounted separately through a proxy so that a sandbox failure does not take down the entire session; Dreaming, meanwhile, is implemented as one managed agent inspecting another agent's history and writing back to memory. The team said that as safety work for model releases has grown heavier, recent efforts have shifted more toward safety, with progress on features such as skills and memory slowing relatively.
Latent Space
Anthropic Engineer Discusses How the Claude Platform Safely Launched Opus 5.5 and Separated Model from Agent Execution
The Latent Space podcast invited Anthropic's Katelyn Lesse and Angela Jiang to explain the engineering behind the Claude platform, including the launch of Opus 5.5, separating the model's "brain" from the agent's "hands," scaling the API, and building reliable hosted agents. The episode also covers rewriting the Messages API in Rust, credential and sandbox isolation, harness design for long-running agents, and safety classifiers and model routing.