this post was submitted on 15 May 2024
445 points (100.0% liked)

TechTakes

1427 readers
131 users here now

Big brain tech dude got yet another clueless take over at HackerNews etc? Here's the place to vent. Orange site, VC foolishness, all welcome.

This is not debate club. Unless it’s amusing debate.

For actually-good tech, you want our NotAwfulTech community

founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 16 points 6 months ago* (last edited 6 months ago) (2 children)

If it doesn't read it on demand, how does it sometimes spill its training data verbatim then?

The trained model shouldn't have that, right? But it does?

https://m.slashdot.org/story/422185

[–] [email protected] 3 points 6 months ago

These models have so many parameters that, while insufficient to memorize all text it has ever seen, it can end up memorizing some of the content. It is the difference between being able to recall a random passage versus recalling the exact thing you need. Both allow you to spill content verbatim, but one is problematic while the other can be helpful.

There are techniques to allow it it 'read on demand', but they are not part of the core model (i.e. the autocmpletion model / LLM) and are tacked on top of it. For example, you can tie it search engine, which Microsoft's copilot does, and is something which I don't think is enabled for ChatGPT by default. Or allow it to query a external data bank (Retrieval Augmented Generation).

[–] [email protected] 3 points 6 months ago (1 children)

Do you read a song on demand when you are singing the lyrics verbatim?