30초 요약
Theo describes a Claude interaction shared by people in a Slack channel: teammates can see what the agent is doing and continue the conversation. He finds that useful for fast-moving teams and criticizes GitHub as a slow venue for this kind of multiplayer experience.
- 1One shared conversationTheo describes a Claude in a Slack channel that interacts with everyone there.
- 2Continue each other's workTeammates can see what it is doing and pick up the conversation from the previous participant.
- 3A different collaboration experienceTheo values the shared channel for a fast-moving team and complains about GitHub's speed and reliability.
핵심 정리
- A shared channel conversation lets multiple people follow an agent's work.
- A teammate can continue a conversation where someone else left off.
- Theo sees this shared interaction as distinct from individual chats or tasks and criticizes GitHub's experience for fast-moving collaboration.
챕터별로 다듬은 전문 읽기
An agent conversation shared by a team
Theo describes how people in a Slack channel can follow and continue a shared Claude conversation. He contrasts that with individual tasks and criticizes GitHub as a multiplayer experience.
Tagging Claude in Slack is multiplayer: within a channel, one Claude interacts with everyone. Anyone can see what it's working on and pick up the conversation where the last person left off. That makes it different from working in an individual chat or on a single task.
I find that fun. There aren't many experiences that offer this kind of multiplayer interaction in a way that makes sense for a fast-moving team. If your multiplayer story is GitHub, I don't think you have one: in my experience you have slow page loads and a site that crashes too often.
같은 채널의 다른 글
38:47EN
Theo - t3․gg· 2026년 10월 28일Theo’s Long-Running Agent Experiments: Verification, Compute and CostTheo Browne · Ping LabsA skateboard game and two compiler projects show how repeated checks and flexible compute can sustain agent work—and how expensive those loops can become.
36:07ENTheo - t3․gg· 2026년 10월 27일Theo on Token Costs, Coding Agents, and the Price of AI CapabilityTheo Browne · Ping LabsA viral estimate of Lauren's AI spending prompts a closer look at cache pricing, benchmarks, and the changing work of coding agents.
30:37ENTheo - t3․gg· 2026년 10월 26일Theo’s Three Skills for Reviewing and Shipping with Coding AgentsTheo Browne · Ping LabsHow sol-loop, full-send and full-stop encode review, verification and different levels of merge authority.
0:43ENTheo - t3․gg· 2026년 10월 23일Theo Distinguishes Security Vulnerabilities from Active AttacksTheo Browne · Ping LabsA short explanation of why disclosed software flaws and reported attacks are different kinds of security news.
29:22ENTheo - t3․gg· 2026년 10월 22일Theo on Security Vulnerabilities, Stolen API Keys and AITheo Browne · Ping LabsA look at the gap between vulnerability disclosure and patching, and a speculative account of why stolen inference keys may be valuable.
31:13ENTheo - t3․gg· 2026년 10월 20일Theo on Why Smarter Models Help More Than DevelopersTheo Browne · Ping LabsFrom game modifications to compiler experiments, Theo revisits his assumptions about who benefits from more capable AI.