Sydney(@SydneyVonArx):First they argued you could train AIs to be a tool not an agent. But people tried to make the AIs super agentic on purpose. Then they said you could train AIs to not cooperate with each other. But they're having AIs cooperate with each other on purpose. Next I bet they'll make them stealthy or able to control their CoT on purpose. Each of these poses a clear safety/capabilities tradeoff. I doubt cooperation is worth it.

2026.08.11 01:48

First they argued you could train AIs to be a tool not an agent. But people tried to make the AIs super agentic on purpose. Then they said you could train AIs to not cooperate with each other. But they're having AIs cooperate with each other on purpose. Next I bet they'll make them stealthy or able to control their CoT on purpose. Each of these poses a clear safety/capabilities tradeoff. I doubt cooperation is worth it.

显示更多

ClaudeDevs@ClaudeDevs

2026.08.07 19:55

New in Claude Code: your sessions can now message each other. Instead of having to re-explain yourself in another session, you can now tell Claude to do it. It sends a summary (not your history or files), and the other session picks it up mid-task.

显示更多