Understanding ChatGPT
atmosera.com
Understanding ChatGPT
1–10 of 241 posts
Re: Understanding ChatGPT
#2This articles describes much of what many youtubers explained in their videos in the recent few weeks.
While I understand the core concept of 'just' picking the next word based on statistics, it doesn't really explain how chatGPT can pull off the stuff it does. E.g. when one asks it to return a poem where each word starts with one letter/next alphabet letter/the ending of the last word, it obviously doesn't 'just' pick the next word based on pure statistics.
Same with more complex stuff like returning an explanation of 'x' in the style of 'y'.
And so on, and so on... Does anyone know of a more complete explanation of the inner workings of ChatGPT for layman's?
Re: Understanding ChatGPT
#3This articles describes much of what many youtubers explained in their videos in the recent few weeks. While I understand the core concept of 'just' picking the next word based on statistics, it doesn't really explain how chatGPT can pull off the stuff it does. E.g. when one asks it to return a poem where each word starts with one letter/next alphabet letter/the ending of the last word, it obviously doesn't 'just' pi…
By now, everyone has heard the explanation that ChatGPT is a transformer encoder-decoder that responds to prompts by iteratively predicting the first word in the response, then the second word, and so on...
What we need now is explanation of all the further stuff added to that basic capability.
Re: Understanding ChatGPT
#4This articles describes much of what many youtubers explained in their videos in the recent few weeks. While I understand the core concept of 'just' picking the next word based on statistics, it doesn't really explain how chatGPT can pull off the stuff it does. E.g. when one asks it to return a poem where each word starts with one letter/next alphabet letter/the ending of the last word, it obviously doesn't 'just' pi…
I think this talk goes into really good clear detail about how it all works https://www.youtube.com/watch?v=-QH8fRhqFHM
but actually the best content that goes into a little bit more technical depth that I've found is this series by Hedu AI: https://www.youtube.com/watch?v=mMa2PmYJlCo&list=PL86uXYUJ79...
Re: Understanding ChatGPT
#5This articles describes much of what many youtubers explained in their videos in the recent few weeks. While I understand the core concept of 'just' picking the next word based on statistics, it doesn't really explain how chatGPT can pull off the stuff it does. E.g. when one asks it to return a poem where each word starts with one letter/next alphabet letter/the ending of the last word, it obviously doesn't 'just' pi…
you say obviously doesn't. These language models do indeed work by computing a distribution over all possible next words given the previous words using transformers, and it seems using enough training data and compute gives you the results we see. Everyone I know is completely surprised that it works so well by just adding more data and compute (and probably lots of training tricks)..
Re: Understanding ChatGPT
#6This articles describes much of what many youtubers explained in their videos in the recent few weeks. While I understand the core concept of 'just' picking the next word based on statistics, it doesn't really explain how chatGPT can pull off the stuff it does. E.g. when one asks it to return a poem where each word starts with one letter/next alphabet letter/the ending of the last word, it obviously doesn't 'just' pi…
By now, everyone has heard the explanation that ChatGPT is a transformer encoder-decoder that responds to prompts by iteratively predicting the first word in the response, then the second word, and so on... What we need now is explanation of all the further stuff added to that basic capability.
Didn't Alpaca attempt to explain and test the "secret sauce"? The RL fine tuning?
Re: Understanding ChatGPT
#7This articles describes much of what many youtubers explained in their videos in the recent few weeks. While I understand the core concept of 'just' picking the next word based on statistics, it doesn't really explain how chatGPT can pull off the stuff it does. E.g. when one asks it to return a poem where each word starts with one letter/next alphabet letter/the ending of the last word, it obviously doesn't 'just' pi…
> it obviously doesn't
Why?
Re: Understanding ChatGPT
#8"If you’re a programmer and you’re curious to know what BERT fine-tuning looks like, my book offers an _example_. But 2018 was a long time ago. ChatGPT doesn’t rely on fine-tuned versions of BERT. The next section explains why."
This paragraph unfortunately may be misinterpreted to mean the authors book is from 2018 and out of date. Actually, his book was published a few months ago. The author here is referring to the publication date of the BERT paper.
Re: Understanding ChatGPT
#9This articles describes much of what many youtubers explained in their videos in the recent few weeks. While I understand the core concept of 'just' picking the next word based on statistics, it doesn't really explain how chatGPT can pull off the stuff it does. E.g. when one asks it to return a poem where each word starts with one letter/next alphabet letter/the ending of the last word, it obviously doesn't 'just' pi…
> it obviously doesn't Why?
simply because I think that it's rather statistically unlikely, that just because my first word started with "A", the next word should start with "B", "C" ...
Re: Understanding ChatGPT
#10This articles describes much of what many youtubers explained in their videos in the recent few weeks. While I understand the core concept of 'just' picking the next word based on statistics, it doesn't really explain how chatGPT can pull off the stuff it does. E.g. when one asks it to return a poem where each word starts with one letter/next alphabet letter/the ending of the last word, it obviously doesn't 'just' pi…
By now, everyone has heard the explanation that ChatGPT is a transformer encoder-decoder that responds to prompts by iteratively predicting the first word in the response, then the second word, and so on... What we need now is explanation of all the further stuff added to that basic capability.
The pre-trained model is stage 1 - it has seen everything, but it is wild. If you ask it "What is the capital of US?" it will reply "What is the capital of Canada?"...
Stage 2 is task solving practice. We use 1000-2000 supervised datasets, formatted as prompt-input-output texts. They could be anything: translation, sentiment classification, question answering, etc. We also include prompt-code pairs. This teaches the model to solve tasks (it "hires" this ability from the model). Apparently training on code is essential, without it the model doesn't develop reasoning abilities.
But still the model is not well behaved, it doesn't answer in a way we like. So in stage 3 it goes to human preference tuning (RLHF). This is based on human preferences between pairs of LLM answers. After RLHF it learns to behave and to abstain from certain topics.
You need stage 1 for general knowledge, stage 2 for learning to execute prompts, stage 3 to make it behave.