You are viewing a single thread.
View all comments View context
5 points
*

It doesn’t read on demand, it reads once when it’s being trained, and it later recalls what it learnt from that training.

Training LLMs takes a very long time and a lot of hardware power.

permalink
report
parent
reply
16 points
*

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

permalink
report
parent
reply
5 points

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).

permalink
report
parent
reply
3 points

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

permalink
report
parent
reply
10 points
Deleted by creator
permalink
report
parent
reply
11 points
*

It doesn’t read on demand

Yes, it does, from the information it was trained on (or - stored), which like you say, requires a lot of hardware power so it can be accessed on demand. It isn’t just manifesting the information out of thin air, and it definitely doesn’t “remember” in the same way we do (E: even the best photographic memory isn’t the same as an indexable one).

permalink
report
parent
reply
6 points

It’s definitely not indexed, we use RAG architectures to add indexing to data stores that we want the model to have direct access to, the relevant information is injected directly in the context (prompt). This can somewhat be equated to short term memory

The rest of the information is approximated in the weights of the neural network which gives the model general knowledge and intuition…akin to long term memory

permalink
report
parent
reply
13 points

or it can be equated to a shitty database and lossy compression (with artifacts in the form of “hallucinations”), but that doesn’t make the tech sound particularly smart, does it?

but half the posts in your history are in this thread and that’s too many already

permalink
report
parent
reply
-4 points

People have such crazy misconceptions about AI. Glad to see someone else knows how it works at least.

permalink
report
parent
reply
1 point
Deleted by creator
permalink
report
parent
reply

TechTakes

!techtakes@awful.systems

Create post

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

Community stats

  • 1.9K

    Monthly active users

  • 565

    Posts

  • 16K

    Comments

Community moderators