@RayFernando1337: Anthropic shipped in silence and the Claude desktop app is crazy good now. Other surprises are Opus 5.5 medium for hard…
Summary
A user praises Anthropic's quiet updates to the Claude desktop app, highlighting Opus 5.5 for hard tasks and vision work, Sonnet for coding, and an orchestration workflow using subagents with remote control.
View Cached Full Text
Cached at: 10/17/26, 02:54 PM
Anthropic shipped in silence and the Claude desktop app is crazy good now. Other surprises are Opus 5.5 medium for hard tasks and it is really good with vision. Most coding tasks just need Sonnet. I stopped using Fable.
I like to orchestrate work so I’m not on my machine or phone all the time so I prompt an ambitions task like…
“I need to update my app for the iPhone Duo and I need to have different display sizes so my app feels intuitive and easy to use for my users. Be sure to look up the Apple Duo group lab transcripts from YouTube and the latest developer documentation. Please spin up multiple subagents to help and you can use Haiku and Sonnet for most tasks depending on difficulty level and reserve Opus for challenging tasks. This main chat serves as the orchestrator or captain. Produce minimal artifacts to survive compaction and handoffs for this long running task.”
Be sure to enable to remote-control so if needed you can check on it while you’re at the beach. This is my Ted talk today. Mahalo.
Similar Articles
@RayFernando1337: Opus 5.5 Medium and I tell Claude Code to delegate subagents and easy work to Sonnet and it’s mind blowing how fast it …
A user shares that Claude Opus 5.5 Medium paired with Claude Code delegation of easy tasks to Sonnet subagents delivers surprisingly fast and accurate results, with the Claude desktop app's memory management greatly improved over terminal use.
Claude OPUS 5.5 is here and Anthropic just cooked everyone this time
Anthropic released Claude OPUS 5.5, boasting impressive performance and a strong price-to-performance ratio that outperforms previous models and GPT.
@interjc: Opus 5.5, pretty good value for money
Anthropic introduces Claude Opus 5.5, a new AI model that performs at the level of Claude Fable 5.1 for most tasks while reducing costs by 40%.
@trq212: before I joined Anthropic, I spent about 2 weeks hacking on this as a side project with Opus 4. It used the Agent SDK s…
An Anthropic employee shares how they ported their side project — a personalized AI-generated homepage — from Opus 4 with the Agent SDK to Claude Managed Agents using a single prompt to Opus 5.5, making it far more reliable.
Opus 5.5 is so good
A post praising the performance of Claude Opus 5.5, highlighting strong positive community reaction to the latest Anthropic model release.