Dr. Mario's 2nd 🧠

What Is ChatGPT Doing … and Why Does It Work

3 min read

rw-book-cover

Metadata

Highlights

for some reason—that maybe one day we’ll have a scientific-style understanding of—if we always pick the highest-ranked word, we’ll typically get a very “flat” essay, that never seems to “show any creativity” (and even sometimes repeats word for word). But if sometimes (at random) we pick lower-ranked words, we get a “more interesting” essay. (View Highlight)

temperature” parameter that determines how often lower-ranked words will be used, and for essay generation, it turns out that a “temperature” of 0.8 seems best (View Highlight)

It’s worth emphasizing that there’s no “theory” being used here; it’s just a matter of what’s been found to work in practice. And for example the concept of “temperature” is there because exponential distributions familiar from statistical physics happen to be being used, but there’s no “physical” connection—at least so far as we know.) (View Highlight)

with 40,000 common words, even the number of possible 2-grams is already 1.6 billion—and the number of possible 3-grams is 60 trillion. So there’s no way we can estimate the probabilities even for all of these from text that’s out there (View Highlight)

So what can we do? The big idea is to make a model that lets us estimate the probabilities with which sequences should occur—even though we’ve never explicitly seen those sequences in the corpus of text we’ve looked at. And at the core of ChatGPT is precisely a so-called “large language model” (LLM) that’s been built to do a good job of estimating those probabilities. (View Highlight)

New highlights added 2023-03-09

There’s nothing particularly “theoretically derived” about this neural net; it’s just something that—back in 1998—was constructed as a piece of engineering, and found to work. (View Highlight)

there’ve been many advances in the art of training neural nets. And, yes, it is basically an art. Sometimes—especially in retrospect—one can see at least a glimmer of a “scientific explanation” for something that’s being done. But mostly things have been discovered by trial and error, adding ideas and tricks that have progressively built a significant lore about how to work with neural nets. (View Highlight)

what was found is that—at least for “human-like tasks”—it’s usually better just to try to train the neural net on the “end-to-end problem”, letting it “discover” the necessary intermediate features, encodings, etc. for itself. (View Highlight)

Graph View