[dead]
[flagged]
Interesting direction. For a self-hosted agentic chat, I'd be curious how you handle long-running sessions and handoffs between users, since that's where these workflows usually get messy in real teams.
The peer-to-peer/outbound-only part is the most interesting bit to me. For coding agents, the tricky part is usually not starting a remote session, but making it clear when the agent is still running, blocked, or has…
Interesting benchmark idea. I'd be curious whether the scoring separates geometry correctness from code maintainability, since generated Three.js can look right while still being hard to edit or extend.
[dead]
[flagged]
[flagged]
[dead]
[flagged]
[dead]
[dead]
[flagged]
[flagged]
[flagged]
[flagged]
[dead]
[flagged]
[flagged]
[flagged]
[flagged]
Interesting direction. For a self-hosted agentic chat, I'd be curious how you handle long-running sessions and handoffs between users, since that's where these workflows usually get messy in real teams.
[dead]
[flagged]
[dead]
[flagged]
The peer-to-peer/outbound-only part is the most interesting bit to me. For coding agents, the tricky part is usually not starting a remote session, but making it clear when the agent is still running, blocked, or has…
[flagged]
Interesting benchmark idea. I'd be curious whether the scoring separates geometry correctness from code maintainability, since generated Three.js can look right while still being hard to edit or extend.
[flagged]