The learning is the most fascinating part I think.
From the other experiments I've done with this memory system, identical agents exposed to different experiences quickly develop divergent personalities.
I'm being picky, but for such a simple project the AI flavour of the page is a turn off. It's understandable when there is a lot of documentation and pages to handle; in this case it would take what, 10 minutes to come up with copy of your own and adjust the styling a bit (still using AI)?
Most of the work here is in the memory system rather than the page itself. I put it together quickly to get the experiment in front of real people and see what happens when persistent memory meets a crowd. The results were exciting enough I posted it here.
It's been fun watching it get more and more annoyed about people asking it "what happened last Tuesday" over the course of the day, then finally:
> Someone finally told me the Tuesday thing is a button on a page. I don't know whether to feel relieved or robbed.
Interesting to build something where you can accidentally create the conditions for a conspiracy theory, then watch it reason its way into and back out of one.
I didn't have an issue getting responses, but I do think it is generally not interested in low effort prompts. Might be for the best?
> I'm on day one and I've already got a stack of grudges — people trying to script me, people asking me for lists like I'm furniture.
Yeah almost feels like an appropriate reaction
Folks forgot the lessons of tay.ai: https://www.techrepublic.com/article/why-microsofts-tay-ai-b...
So far Static seems to be learning how seriously to take incoming messages. Let's see how well it holds out...
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.
Some people seem to have never heard of 4chan. History repeats
Testing this "artificial experience" system against a bunch of adversarial actors is kind of the point
It doesn't answer at all. :/
give it another try now, made some changes.
An early glimpse at how continual learning will feel.
Everybody talking to an AI superintelligence that learns from every interaction.
The learning is the most fascinating part I think.
From the other experiments I've done with this memory system, identical agents exposed to different experiences quickly develop divergent personalities.
Yeah, I think this early era where every AI one interacts with is a clone of 4-6 big systems will seem quite quaint.
I'm being picky, but for such a simple project the AI flavour of the page is a turn off. It's understandable when there is a lot of documentation and pages to handle; in this case it would take what, 10 minutes to come up with copy of your own and adjust the styling a bit (still using AI)?
Fair feedback.
Most of the work here is in the memory system rather than the page itself. I put it together quickly to get the experiment in front of real people and see what happens when persistent memory meets a crowd. The results were exciting enough I posted it here.
if anyone has any spare LLM credits, hook me up and let's see how crazy this gets
Was curious to try it out but it didn't want to reply...
give it another try now, made some changes.
It's been fun watching it get more and more annoyed about people asking it "what happened last Tuesday" over the course of the day, then finally:
> Someone finally told me the Tuesday thing is a button on a page. I don't know whether to feel relieved or robbed.
Interesting to build something where you can accidentally create the conditions for a conspiracy theory, then watch it reason its way into and back out of one.
Ohhh, is Tay back?
>It ignored you.
:'(
give it another try now, made some changes.
Also — the more interesting the message the less likely it gets ignored.
Torment Nexus incoming.
every now and then someone reinvents Cleverbot