Remove articles how-to-use-llms-summarize-long-documents
article thumbnail

ChatGPT, Author of The Quixote

O'Reilly

TL;DR LLMs and other GenAI models can reproduce significant chunks of training data. The narrator tells us that, “the Cervantes text and the Menard text are verbally identical, but the second is almost infinitely richer.” Specific prompts seem to “unlock” training data. This is the basis of The New York Times lawsuit against OpenAI.

article thumbnail

Real-Real-World Programming with ChatGPT

O'Reilly

If you’re reading this, chances are you’ve played around with using AI tools like ChatGPT or GitHub Copilot to write code for you. or “ha look how incompetent it is … it couldn’t even get my simple question right!” This article summarizes what I learned from that experience.

article thumbnail

What Are ChatGPT and Its Friends?

O'Reilly

What is it, how does it work, what can it do, and what are the risks of using it? Maybe it’s surprising that ChatGPT can write software, maybe it isn’t; we’ve had over a year to get used to GitHub Copilot, which was based on an earlier version of GPT. The GPT-series LLMs are also called “foundation models.”

Google 104