Live data from Hacker News

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

izzy.co

331–340 of 371 posts

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

#331
About 15 years ago I'd have a similar-enough chat with a colleague that went the same way every time we had it. It was pointless. We'd polarise the same way every time, so why waste the energy. I proposed (and he agreed) that it would be easier to just turn our perspective into bots that could parrot the usual discussion so we could do something (or talk about something) more useful, unless we actually had some value to add that was non-obvious.

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

#332
post #287

Earlier quoted context omitted.

> If a company is going to snoop in your personal data to get insights about you, they'd just do it directly. Hiring managers would scroll through your e-mails and make judgment calls based on their content. This is like saying, "look, no one would be daft enough to draw a graph, they'd just count all the data points and make a decision." You're missing two critical things: (1) time/effort (2) legal loophole. A targe…

> This is like saying, "look, no one would be daft enough to draw a graph, they'd just count all the data points and make a decision." Not really. Assuming your ethical compass is broken and you suspected your partner of cheating, would you rather have access to their emails or to a LLM trained on them? Also, isn't it much cheaper for Google to simply search for keywords rather than fine tuning a model for this? At l…

[flagged]

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

#333
post #23

In Caprica, the Battlestar Galaticia, spinoff - a dead character was embodied in a robot and trained on social media content... But in the real world, who owns your LLM dupe output after you die?

yes thanks for reminding, I recall something about a cult soldiers of the one creating a perfect 'heaven' for uploaded consciousness of fallen mates. man its getting darker by the day.

technically the 'data' is owned by you but say google has ability to create search databases from it. they could argue the character is their copyrighted work. dont know .. seems like a super gray area.

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

#334
post #23

In Caprica, the Battlestar Galaticia, spinoff - a dead character was embodied in a robot and trained on social media content... But in the real world, who owns your LLM dupe output after you die?

> But in the real world, who owns your LLM dupe output after you die?

If you haven't read it yet, enjoy[1] QNTM's Lena https://qntm.org/mmacevedo - it's a short story that covers ownership of a hypothetical human brain-upload. so not quite an LLM dupe, but a higher-fidelity snapshot of an actual human mind (in the fictional universe).

1. For the lack of a better word

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

#335
post #234

Remember Replika and how people got quite attached to that chatbot? I imagine in the near future you'll be able to sell your and your friends' chat history to a company building a more advanced, realistic chatbot. Do you want to have a group of friends to hang out with? Buy an organically fabricated and pre-trained chatbot. Or maybe there's enough emptieness in your life that you go deep assume one of those friends'…

> Buy an organically fabricated and pre-trained chatbot.

"Robo Billy Mays here. Has your partner dumped you and you can't get over them? It's time to UPGRADE them to a perfect, anatomically correct* specimen. Scan this QR code NOW to get our special subscription price or 299.99/mo"

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

#336
post #23

In Caprica, the Battlestar Galaticia, spinoff - a dead character was embodied in a robot and trained on social media content... But in the real world, who owns your LLM dupe output after you die?

William Gibson wrote about similar stuff in various stories in the collection “Burning Chrome” and in Neuromancer. IIRC, there was an elite hacker whose mind had been saved in ROM, the Dixie Construct, I think. It was helping with a job. It’s reward if they succeeded? It wanted to be erased. Not really a spoiler, just a detail that I was reminded of by this discussion.

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

#337
post #288
post #49

While I love all these stories of turning your friends and loved ones into chat bots so you can talk to them forever, my brain immediately took a much darker turn because of course it did. How many emails, text messages, hangouts/gchat messages, etc, does Google have of you right now? And as part of their agreement, they can do pretty much whatever they like with those, can't they? Could Google, or any other company…

My favorite article to post. The below is about 1% of the topics it covers, the premise being that algorithmic prediction traps us frozen in the past instead of ever allowing society to change. https://www.bbc.co.uk/blogs/adamcurtis/entries/78691781-c9b7... >But the oddest is STATIC-99. It's a way of predicting whether sex offenders are likely to commit crimes again after they have been released. In America this is b…

Link appears to be dead now.

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

#338
post #230

Earlier quoted context omitted.

I agree. I've been looking to train/fine-tune an LLM model myself but the corpus I want to provide is not in question/answer mode. Is there a way to train or fine-tune an LLM model using say only plain text files?

You can use an LLM to rewrite a document to a question answer form.

How would one go about this for a large number of documents?

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

#339
post #49

While I love all these stories of turning your friends and loved ones into chat bots so you can talk to them forever, my brain immediately took a much darker turn because of course it did. How many emails, text messages, hangouts/gchat messages, etc, does Google have of you right now? And as part of their agreement, they can do pretty much whatever they like with those, can't they? Could Google, or any other company…

You might like season 3 of Westworld. Buckle up, humans.

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

#340
post #49

While I love all these stories of turning your friends and loved ones into chat bots so you can talk to them forever, my brain immediately took a much darker turn because of course it did. How many emails, text messages, hangouts/gchat messages, etc, does Google have of you right now? And as part of their agreement, they can do pretty much whatever they like with those, can't they? Could Google, or any other company…

The first instance of this would most likely alienate a lot of users. What is more likely to happen is the development of new products that basically cater to social needs through mimicking real world interactions. Subscribe for 15$ a month to feel like you have an unending flow of conversations with interesting bots that mimic your friends! I am sure there is a market for this. This product could be advertised as a…

Maybe some people can pretend they're interacting with a real person. But for me, knowing that I'm interacting with a bot would break the experience for me.
Post reply on HN