Are you better than a language model at predicting the next word?

Post by raggi » Sun, Aug 18, 2024, 7:33 PM UTC

DiscourseFan wrote: post #53

raggi wrote: post #52

Earlier quoted context omitted.

in the above, when i say llm, i mean the base models, when i say chatbot, i mean things like chatgpt, they're not the same. chatgpt is not just a frontend for the base model, studies on chatgpt covering output biasing that it has from the fine tuning, prompts and contexts and other things they do are largely not applicable to the raw model generation in this quiz, and they are also largely not applicable to llms as a…

An LLM takes a slice of data from the world, by nature it has to organize it in some such way, depending on how its trained, and the method of organizing it is hard-coded into the model. Therefore, all models will develop some sort of style, no matter what, since somebody, or a team of people, had to figure out a way to portion out a selection of data, and this problem is intractable.

Post by fidla » Mon, Aug 19, 2024, 4:58 PM UTC

Post by raggi » Wed, Aug 21, 2024, 6:29 PM UTC

DiscourseFan wrote: post #104

raggi wrote: post #101

Earlier quoted context omitted.

generative models are trained to generate outputs in response to an input, that closely resemble the training data. that’s literally all they do. if a base model was introducing “style” training (as we currently do it) wouldn’t even function. what you’re implying is mathematically intractable for generative models, and that’s fundamental to what they are and how they are made. the style stuff you’re referring to is a…

So you agree with me? Style is fundamentally part of the set of all data used in production, and that can be “tuned” as you say, but never removed. Its the ghost in the machine, the spark of contingency. Of course, all machines bear the mark of their creators, but LLMs doubly so, as creators themselves. Like shitty, partially incoherent children.