31–40 of 95 posts
It really is the only thing that makes sense. Completely sandbox'ed, and treated like the junior programmer who will do, literally, any dumb thing you tell them to do, as long as there is an Issue for it.
I'll be impressed if a Claude and a Codex instance improvise a channel like this spontaneously on their own. Doing this intentionally via prompt doesn't seem very interesting.
When that happens, will it still be impressive/spontaneous? Will we know the difference?
I actually built a memory system off git. https://github.com/ryanthedev/grug-brain.mcp
This is actually so great. I mainly use Claude Code but sometimes I am sending over a message to Codex asking what he thinks of the idea of Claude Code. This can save so much time :D
So I solved this by using NATS and letting each agent pub / sub to the shared message bus.. simple binary you can run anywhere and it's highly useful! Part of a broader tool I created - https://github.com/fjwood69/mori
How do you make the agents actually use the tool? That has been my main problem with most mcp and tools. The agents know about them but don't use them unless reminded to.
I have started sandboxing all AI's in their own VM, and interfacing with them primarily through Jira and Git. It really is the only thing that makes sense. Completely sandbox'ed, and treated like the junior programmer who will do, literally, any dumb thing you tell them to do, as long as there is an Issue for it.
I have started sandboxing all AI's in their own VM, and interfacing with them primarily through Jira and Git. It really is the only thing that makes sense. Completely sandbox'ed, and treated like the junior programmer who will do, literally, any dumb thing you tell them to do, as long as there is an Issue for it.
I'll be impressed if a Claude and a Codex instance improvise a channel like this spontaneously on their own. Doing this intentionally via prompt doesn't seem very interesting.
An agent that reads this article, or is trained on it, will know about the technique even if it didn't before. When that happens, will it still be impressive/spontaneous? Will we know the difference?
I'll be impressed if a Claude and a Codex instance improvise a channel like this spontaneously on their own. Doing this intentionally via prompt doesn't seem very interesting.
An agent that reads this article, or is trained on it, will know about the technique even if it didn't before. When that happens, will it still be impressive/spontaneous? Will we know the difference?