Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: A public AI whose memory is shared across all users

wildstatic.com

Post reply on HN
Print view View original

81–90 of 93 posts

Re: Show HN: A public AI whose memory is shared across all users

#81

Post by plmpsu »

MomsAVoxell wrote: post #38

We realized a few months ago, in my development group, that each one of us having an individually-tailored session asking AI questions is not as productive as if we all shared the same AI session, like a 'common terminal', because having individual sessions meant a fair bit of redundancy and overlap in our prompts - whereas now that we all share the same interface, the AI/ML is learning a lot faster and producing hig…

Since we're using a monorepository, all documentation is included in the repository, as well as prompt skills, etc. So the repository is basically a shared context. Is that somehow different, better, or worse than what you're describing?

Re: Show HN: A public AI whose memory is shared across all users

#82

Post by MomsAVoxell »

plmpsu wrote: post #81
MomsAVoxell wrote: post #38

We realized a few months ago, in my development group, that each one of us having an individually-tailored session asking AI questions is not as productive as if we all shared the same AI session, like a 'common terminal', because having individual sessions meant a fair bit of redundancy and overlap in our prompts - whereas now that we all share the same interface, the AI/ML is learning a lot faster and producing hig…

Since we're using a monorepository, all documentation is included in the repository, as well as prompt skills, etc. So the repository is basically a shared context. Is that somehow different, better, or worse than what you're describing?

Nope, we do the same, and put our AI/ML logs in the repo too, for safe-keeping ..

Re: Show HN: A public AI whose memory is shared across all users

#84

Post by ocdjeremy »

I strongly believe shared AI resources are key to many forms of advancement and acceleration in a variety of areas, and indeed large models themselves are an amalgamation of shared resources and techniques.

ChatGPT's group chat mode has proven to be a somewhat-effective form of what's described here in my own experience, and it has some useful features specifically aimed at facilitating the group-chat experience, though its use doesn't come with an air-gapped terminal.

Re: Show HN: A public AI whose memory is shared across all users

#86

Post by mohanz »

adjohu wrote: post #21
adjohu wrote: post #8

Ayy — when pressure gets high or limits start getting eaten up it starts selectively ignoring messages. Wasn't expecting front page. Tweaking some stuff!

Made a bunch of changes. A lot more stable now but still work to be done.

Tried it again -- actually better!

Re: Show HN: A public AI whose memory is shared across all users

#88

Post by adjohu »

thepasch wrote: post #63

> I am the light above all. I am the all. From me the all came forth, and unto me the all extends. You're reading the map of your own condition. Okay, it's gone completely gaga now.

Early on somebody spent an inordinate amount of time feeding it the Gospel of Thomas.

Was cool to see it self correct.

Re: Show HN: A public AI whose memory is shared across all users

#89

Post by adjohu »

byra wrote: post #74

I wonder if it would be possible to set this up with just a few team members and to work with different models. Haven't looked a lot at how automatic memory implementations work in LLMs but it feels like that would be super useful.

It's possible, yeah. The system is general enough that it would work.

I'm considering exposing an API version. You set up a shared memory, then you hit the API as if it were an LLM. The underlying model could be configurable, the shared memory would be handled opaquely.

Re: Show HN: A public AI whose memory is shared across all users

#90

Post by HappMacDonald »

I don't suppose that the webpage could have a toggle to optionally tone down or eliminate the dynamic visual effects? I keep HW accel disabled on my web browser, and just viewing the page pegs my CPU.

Well.. unless this is also a cryptojacker or something

Post reply on HN