One Developer, Two Dozen Agents, Zero Alignment
maggieappleton.com · 2,971 words · saved by 2 readers
Why we need collaborative AI engineering and a tour of Ace: the multiplayer coding workspace
This talk is the first public demo of Ace – a new research prototype we’ve been building within the GitHub Next https://githubnext.com team. Ace is a realtime, multiplayer coding agent workspace. It’s like Slack, GitHub, and Claude/Copilot had a baby. You work with agents, but also all your coworkers in the same space, sharing chats, context, and all using the same computers in the cloud to do the work. At this point, in early 2026, all coding agents are designed as single player experiences. But building software isn’t a single player game. I talk through why we need collaborative AI engineer
saved by
related reading
- Scaling long-running autonomous coding · Cursorcursor.com
- Why We Built Our Own Background Agentbuilders.ramp.com
- Code was our medium for thoughtwattenberger.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- Now – Updates from the Linear teamlinear.app
- Agentic Coding Ascension Notes – Machine Learning (Theory)hunch.net
- Towards self-driving codebases · Cursorcursor.com
- claude code is not making your product betterethanding.substack.com
- Thoughts on slowing the fuck downmariozechner.at
- The Age of Async Agents — Cognition's Walden Yan & OpenInspect's Cole Murraylatent.space
- SWE-chat: Coding Agent Interactions From Real Users in the Wildarxiv.org
- Vibe engineeringsimonwillison.net