381
ChatGPT's new AI store is struggling to keep a lid on all the AI girlfriends
(www.techradar.com)
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 19 Jan 2024
381 points (98.2% liked)
Technology
59205 readers
2842 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 1 year ago
MODERATORS
I’d love to have an AI assistant/girlfriend like JOI from Bladerunner 2049, something I could jerk off to one minute, then have her prepare my taxes and order a pizza the next. However, these ChatGPT girlfriends all seem like they’re just subscription chatbots. Maybe some day we’ll get there and nerds will work up a local, open-source slutty AI girlfriend, but for now they’re all just crap.
I think you can self host an AI chat not these days
You can, and it's easier than you might think! Check out a platform like Oobabooga and find a nice 4-bit quantized LLM of a flavor you prefer. Check out TheBloke on hugging face, they quantized a ton of great LLMs.
What the fuck did you just say?
What’s an LLM. Is it a new form of pyramid scheme?
/s
What is "quantized"?
https://en.wikipedia.org/wiki/Quantization_(signal_processing)
Roughly speaking: The AI equivalent of reducing bitrate. Works quite well if you're only running them in inference mode and don't want to train them as the networks are quite noise-resistant (rounding all weights is, in essence, introducing noise).
Here's the summary for the wikipedia article you mentioned in your comment:
Quantization, in mathematics and digital signal processing, is the process of mapping input values from a large set (often a continuous set) to output values in a (countable) smaller set, often with a finite number of elements. Rounding and truncation are typical examples of quantization processes. Quantization is involved to some degree in nearly all digital signal processing, as the process of representing a signal in digital form ordinarily involves rounding. Quantization also forms the core of essentially all lossy compression algorithms. The difference between an input value and its quantized value (such as round-off error) is referred to as quantization error.
^to^ ^opt^ ^out^^,^ ^pm^ ^me^ ^'optout'.^ ^article^ ^|^ ^about^
Exactly! If you only want to use a Large Language Model (LLM) to run your own local chatbot, then using a quantized version will dramatically improve speed and performance. It also allows consumer hardware to run larger models which would otherwise be prohibitively resource intensive.
That's neat!
Ah, thanks! I'm only familiar with the word in other contexts so it made a lot of noise.