I wrote a "council" skill that makes my agent argue with Opus 5.5, Muse Wonder Full and GPT-6.1 Sol before it is allowed to merge

Duet's hardest job is deciding when to interrupt you, (like all proactive agents) and Anthropic says it's still tuning that. Its own FAQ warns it can misread a thread, misjudge what's urgent, or miss something that lands between check-ins. Before you join the waitlist: the background check-ins count against your Pro or Max limits. It asks before it sends, pays, signs or deletes, and some actions stay off-limits even with your approval, like moving money between accounts.

Turns out TUI visualizations hold together longer than I expected they would

In college we has `rejection Tuesdays` where you had to try and get rejected. Homies got married left and right

It is becoming f*cking dangerous A 23-year-old dev from China just ran 300 Claude Code agents in parallel and hooked them to a verification layer so none of them could bullshit him He opens the live dashboard: - 300 agents writing and checking at the same time - Every output verified against the source in ~100 ms - Three passes over 100 company profiles → zero errors left - Everything dumped straight into an Obsidian vault The trick is the split: one model does the work, a cheaper one decides if the claim is actually true. The loop doesn’t stop until everything checks out An analyst team would bill weeks for this. He got it in one run Same kind of Second Brain + swarm setup that keeps circulating. Bookmark the full breakdown