tl;dr: One of the tricks to using GPT-4 well is understanding how it sees text and instructions When we started testing GPT-4 internally last summer one of the first tests people would try is getting it to play the game Wordle. While trying to guess a five-letter word should be simple for an advanced language … Continue reading How to get GPT-4 to play Wordle (and other prompt tricks)
ChatGPT + Code Interpreter = Magic
tl;dr: OpenAI is testing the ability to run code and use third-party plugins in ChatGPT. OpenAI has announced that we’re developing plugins for ChatGPT that will extend its capabilities. [Link] Plugins range from third-party tools like WolframAlpha and OpenTable, to our browsing plugin and Code Interpreter that can generate code, run code, upload and download … Continue reading ChatGPT + Code Interpreter = Magic
Collaborative Creative Writing with OpenAI’s ChatGPT
tl;dr: You can use OpenAI’s ChatGPT to bounce ideas around and write story outlines Since I got into the field of AI and started working at OpenAI, it’s been interesting to see how things have accelerated. As an author, I’m frequently asked if AI will replace writers altogether. My personal take is that while AI … Continue reading Collaborative Creative Writing with OpenAI’s ChatGPT
The Easy Guide to Using OpenAI’s Whisper Model to Transcribe Video and Audio
OpenAI recently released Whisper, an open source automatic speech recognition model that's incredibly powerful. I'm biased (I'm the Science Communicator for OpenAI), but in my experience it's better than any system or service I've ever used. Best of all, your can use it completely free, either by downloading it to your computer or by running … Continue reading The Easy Guide to Using OpenAI’s Whisper Model to Transcribe Video and Audio
Building games and apps entirely through natural language using OpenAI’s code-davinci model
https://media.giphy.com/media/vMFgJ4Uq1yqOtuT1Cc/giphy.gif TL;DR: OpenAI has a new code generating model that’s improved in a number of ways and can handle nearly two times as much text (4,000 tokens.) I built several small games and applications without touching a single line of code. There are limitations, and coding purely by simple text instructions can stretch your imagination, … Continue reading Building games and apps entirely through natural language using OpenAI’s code-davinci model
Smarter than you think: Crystalline and fluid intelligence in large language models
Large models like GPT-3 can perform a variety of tasks with little instruction. That said, one of the challenges in working with these models is determining the right way to do something. GPT-3 has acquired knowledge from its training data as well as another kind of “intelligence” from learning the various relationships between concepts in … Continue reading Smarter than you think: Crystalline and fluid intelligence in large language models
How to get better Q&A answers from GPT-3
GPT-3 is an exceptional mimic. It looks at the text input and attempts to respond with what text it thinks best completes the input. If the first line sounds like something from a romance novel it will try to continue writing in that style. If it’s a list of video games, it will try to … Continue reading How to get better Q&A answers from GPT-3
Video: GPT-3 and long lists
https://vimeo.com/552634504 GPT-3 can remember hundreds of items and perform completions with them. This is useful if you want to take your prompts to the next level and do more complex operations.
A simple method to keep GPT-3 focused in a conversation
OpenAI's GPT-3 is a highly capable general language model able to talk about almost anything. While this is an advantage on one hand, it can also make keeping GPT-3 focused on one topic a challenge if you’re trying to create a special purpose chatbot. If you want GPT-3 to talk about movies with a user, … Continue reading A simple method to keep GPT-3 focused in a conversation
OpenAI API Classification Endpoint
We recently added three new endpoints to the API for GPT-3. The Classification Endpoint makes it easy to apply classification from a data set larger than what fits inside a prompt. https://vimeo.com/536638286