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

Replacing my best friends with an LLM trained on 500k group chat messages

izzy.co

Post reply on HN
Print view View original

21–30 of 371 posts

Re: Replacing my best friends with an LLM trained on 500k group chat messages

#21

Post by circuit10 »

xwdv wrote: post #19
syntaxing wrote: post #12

This is awesome, clear and concise explanation. I was talking to my wife and debating whether I should build a model of each of us and store it somewhere in case something tragic happens to either of us. But we decided not to because something about it felt wrong but maybe I’ll make it just in case I regret not doing later on.

You certainly won’t regret it. If you need to get information out of your wife and she won’t cooperate you can coerce the LLM of your wife into having it divulge private information that your wife won’t reveal. This can be very useful for something like a divorce case. Best to find a way to keep the LLM regularly training on new data as well. Edit : stop downvoting ideas you don’t like, that’s not what it’s for.

Not sure if this is a joke but this in case it isn’t, no, that’s not how it works, it will just make up random plausible-ish guesses

Re: Replacing my best friends with an LLM trained on 500k group chat messages

#22

Post by jacquesm »

xwdv wrote: post #19
syntaxing wrote: post #12

This is awesome, clear and concise explanation. I was talking to my wife and debating whether I should build a model of each of us and store it somewhere in case something tragic happens to either of us. But we decided not to because something about it felt wrong but maybe I’ll make it just in case I regret not doing later on.

You certainly won’t regret it. If you need to get information out of your wife and she won’t cooperate you can coerce the LLM of your wife into having it divulge private information that your wife won’t reveal. This can be very useful for something like a divorce case. Best to find a way to keep the LLM regularly training on new data as well. Edit : stop downvoting ideas you don’t like, that’s not what it’s for.

That's beyond creepy.

Re: Replacing my best friends with an LLM trained on 500k group chat messages

#24

Post by sharemywin »

sdwr wrote: post #17

Wish I had friends who talked mild shit like this! All my friends are nerds who take everything seriously. On the project, did you do anything about the time dimension? ChatGPT is strictly input -> output, but something like this needs time between messages to feel real (and not run constantly). I imagine adding "time since last message" to the training data + expected output would work.

wow. did you just call out your friends for being nerdy and say the nerdiest thing I've ever heard?

Not that it's not a cool idea, though.

Re: Replacing my best friends with an LLM trained on 500k group chat messages

#27

Post by m3kw9 »

ryanianian wrote: post #16

Very reminiscent of the Be Right Back episode of Black Mirror [1]. A family member recently died unexpectedly, and I have a small collection of texts, emails, and blog posts by them saved on my machine in the small (perhaps delusional) hope that they'll be a useful training set for a them-flavored chatbot. Perhaps even one that's trained to help me with the grief of their loss. Not a huge amount of training data, tho…

Also, take more videos of everyone as they will very soon be able to create very accurate 3d renderings of people just from videos. More training materials the better, make sure you get full views with different aspects , movements, angles and expression. Creepy, I know.

Then you can interact with these recreated avatars on your vr/ar head sets. Good for kids as when they grow up maybe you can recreate some old times lol

Re: Replacing my best friends with an LLM trained on 500k group chat messages

#29

Post by xwdv »

circuit10 wrote: post #21
xwdv wrote: post #19

Earlier quoted context omitted.

You certainly won’t regret it. If you need to get information out of your wife and she won’t cooperate you can coerce the LLM of your wife into having it divulge private information that your wife won’t reveal. This can be very useful for something like a divorce case. Best to find a way to keep the LLM regularly training on new data as well. Edit : stop downvoting ideas you don’t like, that’s not what it’s for.

Not sure if this is a joke but this in case it isn’t, no, that’s not how it works, it will just make up random plausible-ish guesses

Knowledge is just a series of words in a highly probable order, it will work. The jury will be easily convinced.

Re: Replacing my best friends with an LLM trained on 500k group chat messages

#30

Post by coryrc »

sharemywin wrote: post #20
obblekk wrote: post #10

Great write up, thanks for posting. I’ve been thinking of doing this for myself. One thought that’s haunting: how long before AI friends are more interesting and stimulating than any real person would be, leading people to prefer AI over humans to befriend… Super stimulus to end all super stimuluses?

record an old girlfriends texts but change them so they say what you want.

I think the Orville has something to say about how that turns out. (S02e11)
Post reply on HN