this post was submitted on 25 Nov 2023
1 points (100.0% liked)

Machine Learning

1 readers
1 users here now

Community Rules:

founded 11 months ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] ILikeCutePuppies@alien.top 1 points 10 months ago (8 children)

I think we'll get better models by having LLMs start to filter out less quality data from the training set and also have more machine generated data, particularly in the areas like code where a AI can run billions of experiments and use successes to better train the LLM. All of this is gonna cost a lot more compute.

ie for coding LLM proposes experiment, it is run, it keeps trying until its successful and good results are fed back into the LLM training and it is penalized for bad results. Learning how to code has actually seemed to help the LLM reason better in other ways, so improving that I would expect it to help it significantly. At some point, if coding is good enough, it might be able to write its own better LLM system.

[–] Stabile_Feldmaus@alien.top 1 points 10 months ago (1 children)

But I wonder if the degree of freedom that you have in coding is just too much for RL to work. For Chess and Go or teaching robots how to move you still have a rather finite number of degrees of freedom whereas there should be much more Combinations of code.

[–] ILikeCutePuppies@alien.top 1 points 10 months ago

Maybe a kinda risc language could be used initally and expanded over time although chatgpt is already doing some amazing things with more complex languages.

load more comments (6 replies)