Productivity
Posts tagged with Productivity.
Category
All Categories
Tags
31 more tagsFewer tags
Newsletter
New posts land in your inbox when they publish. No spam, unsubscribe anytime.
You're in. New posts head your way.
Filters1
Category
All Categories
Tags
31 more tagsFewer tags
56 posts
750 tokens a second does not make review faster
GPT-5.6 Ultrafast is 750 tok/s of author speed. That fills the human review queue harder. Pin the changelog to the bottleneck, then budget the review lane.
Auto mode is the default because you already approved everything
Claude Code auto mode is default for new Pro, Max, and Team sessions because you already approved 97% of prompts. Put deny and ask rules in front now.
Claude Code sessions can now message each other
Claude Code sessions can now message each other with a text ping. Use ListAgents for status. Keep the worktree. A ping is not a lock on a shared file.
Enterprise can now pull Claude Code transcripts off the laptop
Enterprise can now pull Claude Code transcripts off a company laptop. The Compliance API rebuilds them from API calls. Treat local as resume, not privacy.
The turf war paper is the sequel to multi-session work
The multiagent turf war paper is the lab sequel to multi-session work. Partition the writers and budget review, or those transcripts become your week.
The watermark fight is about PRs, not essays
The Claude watermark fight is pointed at essays. Claude Code already marks generated text that lands in git, and that is the receipt that now matters.
Ask the agent for a file, not a scrape
Agent workflow skills that name the artifact beat a scrape toolbox. Ask for the audit file, not a page dump, so yesterday's work still opens from disk.
Your Team's Real Product Is Now the Prompt Repo
The team product is now the prompt repository. Version agent instructions and skills in git, review them like code, and keep them thin and reproducible.
The quality risk of caveman is the workspace
The quality risk of caveman is the workspace, not token thrift. Easy daily tasks keep quality. Multi-hop agent work is where dialect load matters most.