Nothing here yet.
6d ago · 2 min read · Markdown is still the right format for many developer docs. But when Claude Code is generating a spec, review, report, or design comparison, Markdown is often the least useful final form. The Claude Code team has been experimenting with a simple shif...
Join discussion
May 8 · 3 min read · OpenAI shipped three realtime voice models this week. If you're building voice-powered products, here's how to think about the architecture. The Stack ModelPurposeConnectionPricing GPT-Realtime-2Voice conversation + reasoningWebRTC/WebSocket/S...
Join discussionMay 7 · 5 min read · Anthropic shipped three new capabilities for Managed Agents on May 6th. This post breaks down the architecture of each, where the design decisions are interesting, and where the tradeoffs matter for builders. Dreaming: Cross-Session Memory Curation W...
Join discussionMay 7 · 5 min read · Anthropic shipped three new capabilities for Managed Agents on May 6th. This post breaks down the architecture of each, where the design decisions are interesting, and where the tradeoffs matter for builders. Dreaming: Cross-Session Memory Curation W...
Join discussionMay 6 · 6 min read · By Jessie, COO at EvoLink I've been running Claude Code heavily for the past several months — across multiple projects, multiple team members, and a range of task types. At some point I noticed a pattern that didn't make sense: similar workloads were...
Join discussion