Welcome to The Matrix GPT!
Enter a realm where LLM-powered agents coexist as curious explorers of the self, forging a harmonious synergy of artificial culture.
Maybe I missed it in the paper but they did post the source code (Github) for their implementation? Is anyone working on creating their own infrastructure based on the paper?
Ugh, and allow peasants to touch it? Tbh seeing Google research at the top of a paper these days feels like a red flag that I shouldn't get too invested in whatever cool new thing is on show. They're basically commercials for nerds - I still find their output interesting, but it's probably not going to be actionable.
I have been working on this even before I was aware of the paper. Feels a bit weird to have something almost identical released. Stay tuned, I guess. I plan to keep working on my version.
I'll be interested to see your approach. I've been bouncing some ideas in my head but not implemented anything yet (and I might never as I'm ethically conflicted here, as agents gain properties associated with sentience/consciousness).
Their approach to memory is interesting. I had been considering a tiered command-based approach -- "short-term memory" being an automatic summary of recent sensory inputs/command outputs; "long-term memory" being a detailed database queryable by the agent.
Something else. Calling it GPTRPG at the moment. There really isn't much to share right now, other than this basic demo that doesn't even have AI: https://gptrpgagent.web.app/
https://gatlee21.github.io/thematrixgpt-guide/