Gaétan Vandenberghe

@ClaudeDevs “Use the word workflow to get started” Translation: “Say the magic word and watch 47 subagents turn your simple task into a venture-backed token bonfire.”

New in Claude Code (research preview): dynamic workflows. Claude writes an orchestration script on the fly, then spins up a large fleet of coordinated subagents in parallel to take on your most complex tasks. Use the word "workflow" in a prompt to get started.

@claudeai “Builds on Opus 4.7”. . . nothing says next-gen, like opening the launch tweet with “we patched yesterday’s failed homework.”

Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors. Available today at the same price.

@claudeai Even making it 3x cheaper, if it still uses as many tokens as 4.7, then GPT-5.5 is probably still cheaper... So hopefully it’s a meaningful bump up this time in agentic coding.

Fast mode is available for Opus 4.8. It's the same model at roughly 2.5x the speed, and we've made it three times cheaper than before. Turn it on with /fast in Claude Code. On the API, contact your account manager to request access or join the waitlist: claude.com/fast-mode

@serenaa_ge Great work! Very interesting, would be amazing to see gpt-5.5 medium and composer 2.5 indeed. Especially since these are the workhorses for most people.

Today we’re releasing DeepSWE, a new standard for agentic coding benchmarks. On public leaderboards, top models often look relatively close in capability. DeepSWE shows where they actually diverge, reflecting the realistic experience of developers in their day-to-day work.