News for hackers. Stuff that matters.
Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by isoprophlex on Thursday March 23, 2023 @04:26PM (#35280839)
Low-rank adaptation (LoRA) ... has some advantages over previous methods:

- It is faster and uses less memory, which means it can run on consumer hardware.

- The output is much smaller (megabytes, not gigabytes).

- You can combine multiple fine-tuned models together at runtime.

This is great news for my dream of building a fine-tuned interactive messenger, that can deliver a message on my behalf by training it on my personality & the information I want to convey.

Now just add text to speech and a talking head, as discussed in that other submission about cloning yourself with AI... https://news.ycombinator.com/item?id=35280418

Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by cal5k on Thursday March 23, 2023 @04:56PM (#35281149)
What if you died but your chatbot didn't know?
Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by BoorishBears on Thursday March 23, 2023 @05:11PM (#35281327)
This is an idea I've been mulling over.

Maybe software running on your PC to capture everything you type, a voice transcriber that filters out your voice specifically and records that, and you've got a dataset that covers a lot of who you are.

Fine tune a model on that and boom, you're "immortal", and as LLMs get better and better, the fidelity of "you" gets better and better.

Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by waboremo on Thursday March 23, 2023 @05:15PM (#35281385)
All the downsides of immortality without any of the fun. As expected from this timeline.
Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by BoorishBears on Thursday March 23, 2023 @05:22PM (#35281475)
No downsides or fun for yourself, the main use I could see for it would be for something like being able to "talk" to your great great great grandpa one day.

It's like home video on steroids

Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by waboremo on Thursday March 23, 2023 @06:28PM (#35282276)
I suppose that is the one retaining upside for the other person when it comes to immortality. But for the individual, none of the immortality fun remains. You aren't meeting or talking to them as you would in "normal" immortality, you are still dead and don't know if they even exist, you don't even get to ensure the right things are passed down.
Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by whoknows234 on Friday March 24, 2023 @04:45PM (#35295198)
So why write letters, time capsules, or leave any other sort of mementos for anyone ?
Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by cloudking on Thursday March 23, 2023 @05:59PM (#35281878)
Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by zer00eyz on Thursday March 23, 2023 @07:12PM (#35282819)
Something like this is a theme in the book Idoru by William Gibson. What happens to the data of a dead person is one theme. Marriage to an AI another.
Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by TehCorwiz on Thursday March 23, 2023 @05:12PM (#35281354)
I'm reminded of this scene from the "I, Robot" movie: https://www.youtube.com/watch?v=ZKxr0wyIic4
Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by elorant on Thursday March 23, 2023 @05:14PM (#35281375)
And then you hook it up to hundreds of dating apps and it just does the boring job of making introductory chat presenting you at the end with only the women who are interested in a real date.
Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by speedgoose on Thursday March 23, 2023 @05:28PM (#35281542)
The problem of this strategy is that your dates may realise that you are not talking as well as a good dating LLM once they meet you.
Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by yieldcrv on Thursday March 23, 2023 @05:36PM (#35281637)
> your dates

> meet you

Everything you said is a net positive for very many people

Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by speedgoose on Thursday March 23, 2023 @05:39PM (#35281668)
Disappointing many people in person isn’t very positive from my point of view.
Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by jrumbut on Friday March 24, 2023 @09:13AM (#35288594)
It was bound to happen to anyway, at least we can make it more efficient
Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by nl on Thursday March 23, 2023 @08:48PM (#35283632)
And then someone uses it to create lots of fake people to populate the app so real people buy more subscriptions.
Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by gravitronic on Thursday March 23, 2023 @08:54PM (#35283669)
My friend was doing this with mIRC scripts on our city's DALnet roo in 2001. His bot hit up random users, asked a/s/l, and if they were female would text to speech "BabyGurl18 is female".

So we'd be watching a movie, he'd have his computer speakers turned up in his room, his bit would announce and he'd get up and leave, already in conversation

Re:How to use Alpaca-LoRA to fine-tune a model like ChatGPT by stavros on Friday March 24, 2023 @02:35AM (#35285743)
When you consider what will happen when everyone on dating apps is an LLM, you see the issue: in the end, everyone is "interested" in everyone who swiped right.