Inpainting with DALL·E 2 is super fun. With some ingenuity, you can create arbitrarily large artwork like the murals shown below – which I assume are the largest
#dalle
-produced images created so far.
Watching our engineering team put out fires scaling this huge model from zero to millions of users over the course of *one* week has been a sight to behold. 💜
We just released a new edit interface for DALL·E that lets you use Outpainting to expand beyond the original borders of an image!
You can use this to make images with different aspect ratios, or arbitrarily large images like murals or magazine covers.
We're hiring folks that have experience with large scale video infrastructure – serving, processing, ingest, etc. If you think you'd be a good match please reach out!
Introducing Sora, our text-to-video model.
Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions.
Prompt: “Beautiful, snowy…
Attempting to generate 2D game assets with
#dalle
.
It definitely works! Getting consistent resolution / aesthetic is likely to be the tricky part.
"science laboratory dungeon, pixel art game scene"
A note to
@OpenAI
developers 🫶:
I wanted to express my appreciation for all the warm, thoughtful, and supportive messages I got and I’ve seen posted across the community.
Despite a moment of uncertainty, our commitment to developers remained steadfast.
In the meantime,…
@mandadorni
I generated a series of smaller images with DALL·E (with each subsequent image having part of the context from the previous images) and then joined them together via separate tooling.
If you have a DALL·E account, you can start using this today. Check out the blog post & guide for more details:
→
→
Kudos
@_chestercho
@joannejang
for superb design & product work on this release!
We're launching Uber Movement Speeds today – a free dataset of historical road speeds aggregated from anonymized Uber trips.
Rolling out now in New York City, London, Cincinnati, Seattle and Nairobi!
Excited to share that I’ve joined OpenAI! I’ll be working on building out the new GPT-3 API () and other projects that help communicate and apply new research.
I built a tool for quickly visualizing data from the command line – say hello to vcli!
Useful for folks working with data that want a fast way to check distributions, outliers, and other statistics.
Check it out:
v4 of the OpenAI TypeScript / Node SDK is out!
Big set of improvements – streaming support (finally), robust types, better file uploads, reduced latency, and a lot more.
➡️
It's been a pleasure collaborating with
@StainlessAPI
folks on this!
Trying something new to kick off 2020 – I’ve been working on a platform that makes it easier to create data-driven apps without code. I’ll be replying to this thread with daily-ish updates on progress.
Small but important decision that has had a very positive impact on company culture in my opinion – it attracts people who are motivated by the mission rather than those chasing titles & status.
When starting OpenAI, we thought hard about what job titles to use—didn't want to bucket people into researchers & engineers. Alan Kay advised that they used "Member of Technical Staff" at Xerox Parc, we loved & adopted it. Recently have seen many companies doing same—very cool!
Generating asset packs could be a good tactic for getting items with similar aesthetic.
{spaceships|science lab|office supplies|food}, 24 pixel art game assets
I spent most of this past weekend experimenting with DALL·E 2, OpenAI’s new AI system that can create realistic images from a written description.
I curated a book of 1000 robot paintings. You can view the entire thing online at
#dalle
Using AI to make faster AI algorithms.
Super impressive research. Also feels like the strongest evidence so far that intelligence explosion is a real possibility.
Today in
@Nature
:
#AlphaTensor
, an AI system for discovering novel, efficient, and exact algorithms for matrix multiplication - a building block of modern computations. AlphaTensor finds faster algorithms for many matrix sizes: & 1/
Some more features:
1. Added state testing data (courtesy of
@COVID19Tracking
)
2. Filters stored in URL for share-ability
3. Dark mode (if enabled in your OS)
Would love to chat with folks who are thinking about proof of personhood – particularly network-based sybil detection. Can grab coffee in bay area or meet virtually, DMs open.
🚨ɴᴇᴡ ꜰᴇᴀᴛᴜʀᴇ ᴀʟᴇʀᴛ🚨
The day ChatGPT launched our ML team got straight to work, asking how it could make
@Intercom
better at Customer Service.
Today we're announcing our first wave of features...
Announced in the last 24 hours:
· Visa developing L2 payment channel on Ethereum
· NFL creating an NFT platform similar to Top Shot
· TikTok releasing NFTs on Immutable X (Eth L2)
Mainstream crypto adoption in progress 👀
The proliferation of public key cryptography as a login mechanism via digital wallets is a great development. Once you sign into a service by connecting your wallet, you realize how silly passwords are.
Signing in with Ethereum wallets is now an available option for all Auth0 clients! A big thanks to our friends (frens?) at
@SpruceID
.
We're excited to see how the Web3 world continues to unlock new tools for identity, privacy, and security:
Looking at daily new cases/deaths over time in a grid view like this feels like the best way to get an overview of the spread – surprisingly I haven't seen any media outlets do this yet.
Had to take a stab at it when I saw the data get released!
We’ve received numerous requests for the data from scientists and government officials who are trying to understand how the virus is spreading and forecast what comes next. So today we’re making the data public for anyone to download and use:
@nicksaraev
@OpenAI
Thanks for reporting this – our team is looking into an edge case where this error might occur. But in general, If you navigate directly to the playground and then click on the Edit mode button, you should be good.
Usually not a fan of the govs negativity towards tech, but the Apple antitrust seems necessary and long overdue.
Surprised it doesn't include competing on your own platform e.g. Apple Music/TV while taxing Spotify & Netflix 15-30%. Platform owners should compete on fair terms.
We are thrilled to announce Imagen, a text-to-image model with unprecedented photorealism and deep language understanding. Explore and Imagen!
A large rusted ship stuck in a frozen lake. Snowy mountains and beautiful sunset in the background.
#imagen
@techsavvytravvy
@OpenAI
This was due to some legacy logic that is no longer needed with our latest models – our team just rolled out a fix!
(and to be clear, this only affected the playground, not raw requests to the API)
@benedictevans
How about monthly Arweave transactions?
People paying to store media/websites/data permanently on a decentralized file storage network. This is business that would otherwise be going to incumbent cloud providers.
Awesome research by the alignment team at OpenAI – fine-tuned GPT-3 model that can summarize entire books, in some cases even matching the quality of human-written summaries.