Exploring the intersection of artificial intelligence and creativity.
The question of how much compute it takes to replace humans in the workforce is unnecessarily reductive. Creating efficiencies does not guarantee humans will prefer a fully automated solution. More so, it does not mean it can’t be outcompeted by an automated solution wielded by a well-networked human. While AI will likely be able to [...]
At this year’s OpenAI Dev Day, I think we saw the next chapter of software unfold. The big headline wasn’t just about new models—it was about an entirely new way of building and interacting with apps. OpenAI’s introduction of AppKit hints at a world where chat itself becomes the operating system. During my time at OpenAI there [...]
Seventy-two hours ago, OpenAI launched Sora, an invite-only app that has already climbed to the top of Apple’s App Store. In just three days, it’s changed how I—and a lot of others—spend time online. Speaking personally, I’ve logged more hours inside Sora this week than I’ve spent on TikTok across my entire life. More than Instagram [...]
For the latest episode of the OpenAI Podcast I sat down with OpenAI president and co-founder Greg Brockman and Code engineering lead Thibault Sottiaux to talk about the release of OpenAI’s new GPT-5-Codex model.
With GPT-4 now stepping back from its starring role in ChatGPT, I want to share a few of my favorite memories from its launch. I originally joined OpenAI as an engineer on the Applied team, but later moved into a hybrid role as OpenAI’s “science communicator.” That shift let me dive deep into technical work [...]
In this video, we delve into the concept of AI hallucinations by comparing them to human cognitive errors. We explore how both humans and AI can make false statements due to incorrect information or reasoning errors. The video explains different scenarios where AI, like humans, can generate incorrect conclusions based on faulty data or assumptions. [...]
tldr: Yes. A recent paper, GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models, makes the claim that their new benchmark demonstrates that state of the art reasoning models have critical limitations when it comes to reasoning. Putting aside the fact that they grouped together tiny 2.7 B parameter models (that could fit [...]
TLDR: There are multiple ways you can use GPT-4 with Vision to power robotics and other systems. I included several sample apps you can download to experiment with including a robot simulator. Multimodal AI models like GPT-4 with Vision have allowed for entirely new kinds of applications that go far beyond just text comprehension. A [...]
TLDR: How to boost GPT-4 with Vision’s capabilities with a simple prompt addition. A recent paper How Far Are We from Intelligent Visual Deductive Reasoning? points out the limitations in visual reasoning in image models like GPT-4V. Like other related papers, I think the investigators are directionally correct (these models don’t have human-level reasoning and [...]
A recent paper The Reversal Curse points out an apparent failure in large large language models like GPT-4. From the abstract: We expose a surprising failure of generalization in auto-regressive large language models (LLMs). If a model is trained on a sentence of the form “A is B”, it will not automatically generalize to the reverse direction [...]
tldr: Custom instructions let you provide ChatGPT with relevant information of your choice about you and how you like to communicate. I’ve use a couple simple tricks to adapt it to my style. I use ChatGPT non-stop for work, fun and exploring. When I write novels it’s a great research helper. When I code it’s [...]
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 [...]
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 [...]
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 [...]
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 [...]
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, but [...]
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 [...]
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 [...]
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.
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, [...]
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.
TL;DR: In an API call GPT-3 can recall details from a 1,500 word article and even repeat passages verbatim. It can also repeat over 250 items from a list as it creates a completion. The concept of memory with a large language model can be a little fuzzy. There’s how much information the model possesses [...]
TL;DR: For many tasks you don’t need to provide GPT-3 with examples because it already understands what you want. If you look closely at the documentation and prompts for GPT-3 provided by OpenAI you’ll notice that a number of them don’t require any examples to show the model what you want. This is because in [...]
TL;DR: GPT-3 is much more capable than people realize when you utilize advanced prompt design that shows it what you want performed in a task then show it how to perform this task with a list of inputs. One of my favorite prompts in our OpenAI documentation is an example showing how to get GPT-3 [...]
Here’s a fun fact: OpenAI’s GPT-3 is actually a family of models, Ada, Babbage, Curie and Davinci that have different capabilities and speed. While Davinci gets most of the attention, the other models are amazing in their own way. Davinci is the most generally-capable model that’s exceptional at intuiting what someone wants to accomplish while [...]
When the first demos of GPT-3 content started to circulate it showed the amazing potential for a really smart language model to generate text and do cool things. Yet despite all the attention GPT-3 has been getting there’s one other aspect of it made available by OpenAI that’s been almost completely overlooked: Semantic Search. The [...]
OpenAI’s API allows for incredibly intelligent text comprehension and transformation. For fun I made a little application that takes a transcript or script and turns it into a narrative structure for a novel and vice versa. This means that you can input dialog and add some simple instructions and get a narrative form back (and [...]
OpenAI’s API is incredibly versatile at comprehending text and completing passages, finding data and generating new information. For fun I wanted to see what would happen if I supplied it with a different kind of text data: Emojis. Emojis are interesting because they can convey information visually and are understood around the world regardless of [...]
I’d like to show one of the API’s other superpowers: Its ability to expand a small thought into a larger expression.
Will artificial intelligence ever write a novel? I believe the answer is “Yes.”
A few years ago I built an app for dictation that was intended to solve one of the biggest frustrations I had with other dictation applications: They didn’t handle punctuation. As a writer I dreamed about just speaking my stories aloud, but the cold hard reality was that until recently, every dictation application required you [...]
OpenAI’s API is incredibly adept at picking up patterns in text. From determining the format to the context, it only takes a little bit of input to get amazing results. In another post I showed how the API was able to complete lists of fictional characters, determining that it’s a list, a list of DC [...]
A few months ago a remarkable thing happened: I got a glimpse of the future. OpenAI, a group of artificial intelligence researchers working towards developing benevolent AI gave me early access to a new API they were developing that would allow developers to utilize the most powerful text generator ever. For background, a text generator [...]
1. Noise-cancelling headphones I use my Apple AirPods Pro whenever I want to tune out the world. They’re not cheap (around $250), but they’re an important part of my writing process. They make external noises much quieter and keep me very focused. They’re great on an airplane and wonderful just sitting in a room by [...]
TL;DR: I wrote a 50,000 word novel in less than 24-hours using dictation. “You can drive a car with your feet if you want to; it don’t mean it’s a good f*cking idea!” – Chris Rock Disclaimer #1: Quantity is no substitute for quality… Disclaimer #2: Sometimes deadlines happen. Sometimes you’re in a rut and [...]