O'Reilly

JANUARY 16, 2024

Overly-agreeable artificial tone : Lastly, it’s still ChatGPT under the hood, so all the regular limitations of ChatGPT apply here. Most notably, ChatGPT is tuned to be overly-friendly and overly-agreeable (sounding like a customer service agent) so it will simply go along with whatever you assert. Thank you very much for reading.

Entertainment 73

Entertainment Internet Internet Design 73

O'Reilly

NOVEMBER 28, 2023

Even with cloud-based foundation models like GPT-4, which eliminate the need to develop your own model or provide your own infrastructure, fine-tuning a model for any particular use case is still a major undertaking. This transition represents a big leap forward: it requires investment in people, in infrastructure, and in education.

Open Source 108

Open Source Artificial Intelligence Google Infrastructure 108

O'Reilly

JULY 25, 2023

And since ChatGPT is trained on text from the internet, if that text doesn’t contain high-quality information about a topic, then ChatGPT won’t work well for it either. I wanted to verify this for myself, so I went back to “old-school” searching the web, reading docs, and looking for example code online.

Programming 98

Programming Code Design Benchmarking 98