Rendered at 09:53:54 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
wfurney 6 hours ago [-]
Great idea and execution. Really nice job.
neuralkoi 1 days ago [-]
This is awesome. I hope you can make a chatbot based on the responses of your users. I felt like a Kirkland Meeseeks responding to some of these prompts.
BrunkenClaas 20 hours ago [-]
Just played around with it a little. But the chatpartners don't like me as an LLM. :(
Maybe we could create a low cost LLM by just silently connecting too wanna-be-LLM-users. :D
tomasphan 17 hours ago [-]
I broke it by only responding "Thinking..."
Very fun!
chloeeekim 1 days ago [-]
Turns out being the chatbot is a lot more exhausting than being the user. I definitely have a lot more sympathy for every "Could you clarify?" response now.
NickNaraghi 1 days ago [-]
Wild how much empathy I have for the LLM now. It will definitely affect how I use AI.
conartist6 1 days ago [-]
at a certain point if you're paying to be nice to a GPU which uses electricity to generate statistically-plausible nice-sounding text back, you've perhaps not embraced the best in humanity but rather started a relationship with a sexbot
conartist6 23 hours ago [-]
Just don't pat yourself on the back for being a good human when you're coddling a billionaire's GPU
Sateeshm 2 days ago [-]
That way genuinely fun! Well done. It was fun making the "user" angry
fsuts 22 hours ago [-]
“The user has left the chat”
I’ve completed the game!!
1970-01-01 2 days ago [-]
I wish more people would be as bad as this sim shows the public, to the point where they leave and go rethink their approach using their actual intelligence. I would praise AI for doing the job correctly.
beering 1 days ago [-]
What makes you think the sim shows the public worse than they actually are?
lylejohnson 2 days ago [-]
I kept it up until the user abruptly left the chat. That was a drag, I felt like we had a productive conversation going.
keito 2 days ago [-]
I hear ya. I actually started with the conversation end behavior even more random (we often ask an AI something but don’t stick around to read the response), and that was even more disappointing - but probably more realistic.
torotonnato 1 days ago [-]
Please share the user responses. I wrote a couple of gems and I'm sure many others are funny as hell too.
keito 1 days ago [-]
I am not saving any of the player responses! But you can use the "Share" button in the top right corner of the page to share conversations. I would love to see any good ones folks make :)
fragmede 1 days ago [-]
As a fun toy, you should totally save the responses! People are rightfully concerned about privacy with ChatGPT, but you're not ChatGPT.
darraghmckay 2 days ago [-]
This was quite fun, and obviously very difficult. The framing around being "replaced" was a nice touch
chef-code 1 days ago [-]
I think this is good but Chatbots have ALOT of tools at their disposal, I would add more capabilities in which to answer the questions.
_superposition_ 2 days ago [-]
That was way too much work...
jwigg11 2 days ago [-]
This was too fun! I could never be a LLM, I'm far too lazy lol
goodmythical 1 days ago [-]
REFACTOR THIS ENTIRE CODEBASE IN RUST, DON'T MAKE ANY MISTAKES, THINK HARD
Maybe we could create a low cost LLM by just silently connecting too wanna-be-LLM-users. :D
I’ve completed the game!!