Nostr Web Client

Depends on the language and/or support. Could be that someone figure it out through a conversation or a guess or checking site package source code or decompiling code. Or if it’s truly a closed source project, via a client support rep. Ultimately someone posts about it somewhere and then chaptgpt knows the new argument.

mark tyler 2y ago

Yeah, I think the only reason we aren’t 100% on the same page, is I tend to talk about its capabilities if we allow it out of its sandbox.

Not sure if you’ve played with AutoGPT or seen the plug-in things people have done. For the sandboxed tool most people use - I’d agree, it’s frozen in time and unable to ask anyone for support.

Thinking more generally about its capabilities, I think it could handle all that. AutoGPT for example could find the contact info of the rep, and ask them what’s going on

Reply to this note

Please Login to reply.

Discussion

mark tyler 2y ago

Also, we’re talking about GPT-4 right?

Katie 2y ago

Right! But it’s still relying on a human in this context. Maybe it breaks our current ecosystem by not then storing that information into a publicly accessible place like stack overflow and makes us dependent on the knowledge or hordes. But what you’re describing still required missing data to be provided to it by a human.

mark tyler 2y ago

That would still be an issue if another AI created the missing data and hadn’t shared it yet. So AutoGPT could for example be asking the other AI what the latest info is if an AI made it not a human.

Katie 2y ago

Data sharing negotiations for and by AI systems 🤣

HoloKat 2y ago

What makes you think it’s running in a sandbox? It’s literally interfaced with human agents who carry out its wishes 😂

mark tyler 2y ago

😂