Re:Are language models deprived of electric sleep?
by the8472 on Wednesday July 27, 2022 @11:05AM
(#32251343)
> and no one is actually testing what proportions of results those are
The idea that models could possibly overfit the training data is hardly a new idea. It's standard practice to test for that. Check section 7 of the PaLM paper for example. https://arxiv.org/abs/2204.02311
Re:Are language models deprived of electric sleep?
by benreesman on Saturday July 23, 2022 @08:15PM
(#32208928)
Copilot is weird.
The N in the NLP training set and arch implies a fuzzy match.
Why anyone would rather start with a plausible but broken-in-a-subtle way buffer rather than a blank one is beyond me.
Copilot spitting out a function out of its training data with changed variable names to match those in your file(s) - and no one is actually testing what proportions of results those are - is still regurgitation.