Steven Adler @sjgadler Twitter profile

Pinned Tweet

Steven Adler

2 years

DALL-E 2 is *leaps and bounds* better at image generation than its predecessor, which was already state-of-the-art. A thread with some notable comparisons: #dalle

5

37

232

Last Seen Profiles

@Hufonime

@MercedesAMGF1BR

@ReiKanouni

@TELFARGLOBAL

@bread_doppio

@poddelaspodcast

@cfvanguard_en

@larysson__

@cryptodataspace

@woodz_yum

@IcarusFellAgain

@nekoame_pink

@viral1nd0

@Doctor_Red_Fox

@aerithisbaby

@_grsk_

@vivo_indonesia

@tsuneysub

@SpineTharin

@WintiwindRustle

@thetraehannibal

@IsraelinToronto

@myhertim

@_kairiichan

@thefepodcast

@TheJaclynTaylor

@carolaam

@UNC_Pleiades

@vascomics

@hex_info

@berabow_cute

@tad55kawasaki

@YingdaoZE

@digital_bathtub

@gangtaehye77398

@TheoCrusaderr

Steven Adler

@sjgadler

5 months

Deeply respect the public reversal on this. It has pained me to see how Ilya has been portrayed in media: I find him so thoughtful and earnest in trying to do right; he also seemed absolutely distraught in the wake of Sam’s dismissal, not coup-like in the least. Again, respect.

Ilya Sutskever

@ilyasut

5 months

I deeply regret my participation in the board's actions. I never intended to harm OpenAI. I love everything we've built together and I will do everything I can to reunite the company.

7K

4K

33K

8

11

264

Steven Adler

@sjgadler

5 months

💜

Sam Altman

@sama

5 months

i love the openai team so much

5K

4K

74K

3

6

220

Steven Adler

@sjgadler

5 months

@ilyasut , in addition to being a prolific AI researcher, is also a very talented artist: Check out the signatures on the paintings in the back

Ilya Sutskever

@ilyasut

5 months

❤️

471

236

7K

9

4

158

Steven Adler

@sjgadler

5 months

We should get a decibel meter for @sama ’s first appearance back at an All-Hands - it’s going to be ⚡️⚡️⚡️

OpenAI

@OpenAI

5 months

We have reached an agreement in principle for Sam Altman to return to OpenAI as CEO with a new initial board of Bret Taylor (Chair), Larry Summers, and Adam D'Angelo. We are collaborating to figure out the details. Thank you so much for your patience through this.

6K

13K

67K

1

0

67

Steven Adler

@sjgadler

1 year

Proud to work for a company where so many unconventional-but-important things get said: Not just privately, but by the CEO, in writing. (1/n)

Sam Altman

@sama

1 year

Planning for AGI and beyond:

242

707

4K

2

64

Steven Adler

@sjgadler

1 year

A very underrated use-case I'm not seeing much of: ChatGPT DJ! Pick a vibe or motif, and have GPT pull a playlist together for you

1

11

53

Steven Adler

@sjgadler

2 years

I was an eye-witness to this - absolutely wild:

Seth Weintraub

@llsethj

2 years

Welcome to the future. Cop pulls over driverless car (because no lights?) Then Cruise goes on the lamb. (via )

814

6K

25K

1

6

41

Steven Adler

@sjgadler

2 years

Ready Player Corgi: coming soon #dalle

4

3

41

Steven Adler

@sjgadler

2 years

Excited to share more about GPT-3 safety and what we've been working on at @OpenAI :

1

33

Steven Adler

@sjgadler

2 years

There's rightfully been a lot of buzz about DALL-E 2's image-generation abilities so far, but I've less about its amazing Variations feature. In just a few cycles, you can go from an image like this (left), to several like this (right):

1

3

27

Steven Adler

@sjgadler

1 year

We’re testing an important step forward: AI optimized for helping w/ goals via chat, & reducing some of the most common issues w/ these AIs (“hallucinating” facts, inappropriate requests, etc). Help test it out & you could win $500 of API credit in our feedback contest!

OpenAI

@OpenAI

1 year

Try talking with ChatGPT, our new AI system which is optimized for dialogue. Your feedback will help us improve it.

1K

3K

13K

5

1

27

Steven Adler

@sjgadler

2 years

We start by erasing the region we'd like to inpaint, then give DALL-E 2 a caption to generate toward. With a little AI inspiration, we can give that old guitarist a shiny new neon pink electric guitar!

1

3

24

Steven Adler

@sjgadler

2 years

With famous paintings, DALL-E 2 can often do in a single-shot what might have taken dozens before, and at significantly higher quality. Can you guess the caption for the below? (Ok, it's listed, but don't cheat!)

3

1

23

Steven Adler

@sjgadler

5 months

Who wore it better?

Greg Brockman

@gdb

5 months

we are so back

2K

4K

52K

2

0

20

Steven Adler

@sjgadler

2 years

We've learned a lot from deploying large-scale AI systems, and attempting to do so responsibly. Now, a bunch of colleagues and I have written up some reflections so they're in the public record and can help others more widely:

OpenAI

@OpenAI

2 years

Deploying and studying the real-world use of language models helps us learn more about safety and misuse than research alone. As we advance our safety and policy work, we're sharing some of our findings to help others do the same.

31

105

457

0

1

19

Steven Adler

@sjgadler

1 year

A major part of OpenAI's Charter is to not unduly concentrate power. It would be quite undesirable for one private group to choose all of AI's values; that is not OpenAI's plan! Read more about how we're building public input and accountability into the design of our systems.

OpenAI

@OpenAI

1 year

Information on ChatGPT’s alignment, plans to improve it, giving users more control, and early thoughts on public input:

484

658

3K

0

3

20

Steven Adler

@sjgadler

5 months

@robertwiblin p(doom) = 0 is such a wild claim. I wonder how many are expressing a view like "I think we'll fix it b/c we'll take it seriously, therefore it's extremely low-risk", vs "I think we're currently on track to solve it" or "there's nothing even in need of solving"

1

0

20

Steven Adler

@sjgadler

2 years

Next, let's try to change the apple into another fruit - say, a bunch of red grapes. This is a bit hard, because the leaves in the original don't quite match what a bunch of grapes looks like. Nonetheless, DALL-E 2 is able to do it. I erase the apple's region, and get these back:

2

0

17

Steven Adler

@sjgadler

2 years

And for those wondering - it isn't just adaptations of famous paintings! @dabmely came up with one of my favorites; the level of detail is pretty stunning, even for my having seen hundreds if not thousands of these:

1

3

16

Steven Adler

@sjgadler

2 years

@ESYudkowsky @nickcammarata Not sure the *exact* prompt Nick is using, but I'll scoop him and give an example:

2

0

15

Steven Adler

@sjgadler

5 months

We make an important side-point in this paper, one that I fear is too often overlooked: AI systems don't need to better than you to be extremely useful, nor do they even need to be just as good. They just need to offer *comparative advantage*, in safe, reliable ways.

OpenAI

@OpenAI

5 months

Our new research white paper identifies seven practices for keeping increasingly agentic AI systems safe and accountable as they become more common and more capable. We are providing research grants for work on a range of open questions.

549

414

2K

0

2

15

Steven Adler

@sjgadler

2 years

With a little creativity and @_dschnurr magic, I was able to make these "larger than life" #dalle images: stitching together different 1024 x 1024 images to create mural-like artwork. Below, a Noah's Ark of robotic animals, & a sandy beach at sunset.

David Schnurr

@_dschnurr

2 years

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.

93

500

3K

2

1

15

Steven Adler

@sjgadler

2 years

@sama Thinking about the All-Hands with the Inpainting demo ... One of the cooler moments of my professional life so far

0

15

Steven Adler

@sjgadler

2 years

@patio11 @sama Here's the Chicago one; at first, this wasn't recognizably Chicago, so I gave it a landmark and this came out a bit better; I then generated some Variations on my favorite:

1

14

Steven Adler

@sjgadler

2 years

@ericjang11 For now, non-commercial uses only! But the future of AI-generated art is looking pretty wild, isn't it

DALL·E 2

Experiment with DALL·E, an AI system by OpenAI

labs.openai.com

3

0

14

Steven Adler

@sjgadler

1 year

GPT-4 is officially out! Here are some of the cool things it can do, and some of the mysteries that remain:

OpenAI

@OpenAI

1 year

Announcing GPT-4, a large multimodal model, with our best-ever results on capabilities and alignment:

2K

18K

64K

2

12

Steven Adler

@sjgadler

2 years

The future's so bright, we've got to wear shades ("3D rendering of a happy robot wearing sunglasses, shallow depth-of-field, tropical celebratory background")

2

0

12

Steven Adler

@sjgadler

2 years

It might be fun to create some Variations on that image, so we aren't working from an *exact* copy. Here's what DALL-E 2 produces: Not bad! But I prefer the original, so let's stick with that.

1

0

12

Steven Adler

@sjgadler

2 years

Sometimes, especially with a tricky concept, generating Variations will turn up some really beautiful ones. So I pick my favorite from the above, and ask DALL-E 2 to create some more that are similar to it - and it produces this:

1

0

12

Steven Adler

@sjgadler

2 years

I'm honored to have worked on this, especially on ensuring that DALL-E 2 leads to delight and increased AI understanding in the world, rather than harm (disinformation, bias, etc). Our amazing Policy Research team did a great job explaining our approach:

1

0

12

Steven Adler

@sjgadler

2 years

Huge kudos to @Miles_Brundage for his leadership of this within OpenAI; honored to have played a small part

Miles Brundage

@Miles_Brundage

2 years

Very excited to share something lot of folks have been working on for a while - an initial set of recommended best practices for language model deployment. Much more to be done and said here but excited for this statement to help move discussion forward!

10

6

78

1

0

12

Steven Adler

@sjgadler

2 years

@patio11 @sama The goldfish one is tricky; even my adapted prompt doesn't do much better, nor do Variations on my favorite of it (the hallucinated text in the original here is very funny):

1

0

12

Steven Adler

@sjgadler

2 years

But eh, where's the fun in another stodgy portrait of a man with grapes and a red party hat obscuring his face? So trite and cliched. Let's do ... a corgi!

2

0

11

Steven Adler

@sjgadler

5 months

How deep will the photo chain go??

Jason Kwon

@jasonkwon

5 months

@sama

408

764

18K

0

10

Steven Adler

@sjgadler

2 years

I'm up for taking some #dalle requests, especially focused on really beautiful or creative artwork. Drop some ideas in-thread, and I'll share out the most-voted ones!

35

1

10

Steven Adler

@sjgadler

2 years

Once upon a time, we developed the technique called "Inpainting", which let you not only generate a novel image from text, but *edit* an existing image to look more like your caption. With painstaking iteration, it was possible to create images like the below.

1

0

10

Steven Adler

@sjgadler

2 years

@ESYudkowsky @nickcammarata And this is one I happen to get if I say the painting is by Eliezer Yudkowsky, though the system on the whole doesn't appear to know what you look like:

2

0

10

Steven Adler

@sjgadler

1 year

I think the world would be far better off if other AGI outposts adopted these norms. Some basically have! @AnthropicAI is a B-Corp, which I love & find far more comforting than "maximizing shareholder value". (3/n)

1

0

8

Steven Adler

@sjgadler

3 months

I’m proud of the investments we’ve made here: Developing a careful, rigorous protocol that will continue to be useful into the future.

OpenAI

@OpenAI

3 months

We are building an early warning system for LLMs being capable of assisting in biological threat creation. Current models turn out to be, at most, mildly useful for this kind of misuse, and we will continue evolving our evaluation blueprint for the future.

173

346

2K

1

0

8

Steven Adler

@sjgadler

1 year

Pro-tip: The best transcription in the world is now available *for free* in the ChatGPT iPhone App.

Introducing the ChatGPT app for iOS

The ChatGPT app syncs your conversations, supports voice input, and brings our latest model improvements to your fingertips.

openai.com

2

0

9

Steven Adler

@sjgadler

2 years

Et voila! We've gone from one classic to one that's sure to be another.

1

0

8

Steven Adler

@sjgadler

2 years

One more for good measure: "3D stained glass window of a happy robot wearing sunglasses, shallow depth-of-field, tropical celebratory background"

1

0

9

Steven Adler

@sjgadler

2 years

@patio11 @sama Here's an illustrative generation re: "A young girl staring down a dragon, who is visibly amused."; this worked on the first shot. Note that the human face which isn't perfect, which IMO is a feature rather than a bug at this stage: see

1

0

9

Steven Adler

@sjgadler

2 years

Truly one of the great privileges of working at OpenAI is a front-row seat to what folks are building, internally and on our platform (and building the things yourself!)

Sam Altman

@sama

2 years

I have now gotten enough of a taste of AI-powered creative tools to know that they're going to be much better than even the AI optimists think. So cool to just think of ideas and iteratively have the computer implement and build on them.

71

184

2K

0

8

Steven Adler

@sjgadler

2 years

The Very Hungry Corgi

1

0

8

Steven Adler

@sjgadler

2 years

This is so cool to see - would love to hear about any other #dalle2 prototypes that folks have worked up in real-life

Paul Yacoubian

@PaulYacoubian

2 years

My 4 year old designed cute fuzzy red chicken slippers with #dalle a couple weeks ago. 🤩 I had them custom made and they just arrived. Soooo cute 🥰 She named them Henry and Wendy 🐓🐓 This is the future of creativity, young entrepreneurship, fashion design and ecommerce.

8

27

212

1

0

8

Steven Adler

@sjgadler

2 years

This is a *very* cool concept - think how much would need to spent on designing fancy mockups in an alternate scenario

Will Davis – 🇺🇸/acc

@wlldvs

2 years

E Brady St (Milwaukee, WI)

32

243

3K

1

0

7

Steven Adler

@sjgadler

2 years

For those curious, I'll show an end-to-end process of creativing something fun. Art was never my strong suit, but with DALL-E 2, I can now "paint my imagination". Let's start with a classic like this:

1

0

8

Steven Adler

@sjgadler

2 years

If you're interested in previewing our research and playing with the AI to help us explore the capabilities of highly-advanced image-generation, you can join the waitlist now:

DALL·E 2

Experiment with DALL·E, an AI system by OpenAI

labs.openai.com

1

0

8

Steven Adler

@sjgadler

1 year

If you want to give GPT-4 a go, you can do so now via ChatGPT Plus: And if any of this sounds interesting, note that we're hiring and would love to hear from you:

Careers

Developing safe and beneficial AI systems requires people from a wide range of disciplines and backgrounds. We’re always looking for curious minds to join our team.

openai.com

1

0

5

Steven Adler

@sjgadler

2 years

Proud to work with @RosieCampbell @Miles_Brundage @GretchenMarina @Fraser @npew @jachiam0 and so many others who were vital to this launch

0

7

Steven Adler

@sjgadler

2 years

This is the AI use-case we’ve all been waiting for

The Wall Street Journal

@WSJ

2 years

The expert ham sniffer of Spain smells 800 hams a day during the Christmas season. He is strained, he said, “at the limit of human possibility.”

232

1K

6K

0

7

Steven Adler

@sjgadler

2 years

DALL-E 2 can also make use of Inpainting, when an image isn't quite well-known enough to be generated de novo. Consider these attempts at generating The Old Guitarist by Picasso; they don't look quite like the original. Thankfully, we can edit the original if we wish!

1

0

7

Steven Adler

@sjgadler

2 years

The Corgi in the Hat

0

6

Steven Adler

@sjgadler

2 years

@sloanesloane Here's the second I chose: You can see it has some trouble getting the "three panes" exactly right (many have two) and the fine details aren't tremendous, but I think the general style is there!

3

0

6

Steven Adler

@sjgadler

1 year

@Bob_Wachter @shawnchitnis @KPIXtv @Bob_Wachter how sure are you that KN95 is real? I don’t see a GB marking on it!

12 Signs You Have a Fake N95, KN95, or KF94 Mask

Counterfeit medical-style masks may leave you less protected. Here’s what to look out for so you don’t waste money on fakes.

www.nytimes.com

1

0

6

Steven Adler

@sjgadler

2 years

The new image-generation system from @OpenAI that'll make you want to dance #dalle

1

0

6

Steven Adler

@sjgadler

1 year

This makes use of our Whisper speech-to-text technology, which I've written about previously here:

Steven Adler

@sjgadler

1 year

One of the best kept "secrets" at OpenAI: Clicking this button at gets you access to instant, world-class transcription. And now, you can do this at scale with our Whisper API.

2

1

4

1

0

5

Steven Adler

@sjgadler

1 year

One of the coolest parts? OpenAI's corporate structure. Capped profits; governed by a non-profit Board; ability to cancel all shareholder obligations if responsibility calls for it. (2/n)

1

0

5

Steven Adler

@sjgadler

2 years

@_markhudson_ Hmm someone asked for "The Creation of Adam by Michelangelo but the humans are cyborgs", but I don't see their Tweet anymore. Maybe they'll see this?

0

6

Steven Adler

@sjgadler

2 years

Ok, great, so we have grapes! But that hat is kind of boring, why don't we try a red party hat instead? Again, start by erasing, and give DALL-E 2 a prompt:

1

0

6

Steven Adler

@sjgadler

2 years

You can read more here about our Content Policy, which applies to DALL-E 2: It's great to see this getting highlighted in news coverage as well, not just the technical features:

OpenAI’s DALL-E AI image generator can now edit pictures, too

OpenAI hopes to release it publicly after testing.

www.theverge.com

1

0

6

Steven Adler

@sjgadler

2 years

That dog in r2c3 is really calling out to me; the neckline isn't quite what I want though, and on further thought, I want a fun vibrant setting like the beach, rather than a solid-colored wall:

1

0

6

Steven Adler

@sjgadler

5 months

@AISafetyMemes Are these quotes attributed as being from distinct individuals? If they're in fact many from the same individual, I think it would be clearer and more-accurate to indicate that with "...." as is the journalistic norm :-)

1

0

6

Steven Adler

@sjgadler

2 years

@bakztfuture Just a note - this is 50 *requests* (multiple images per request), not 50 images; please let us know if you're seeing something different, would definitely want to patch that

1

5

Steven Adler

@sjgadler

6 months

@BorisMPower @janleike @janleike how do you keep the concepts straight normally? FP vs FN? (Precision starts with a P & is related to FP)

0

3

Steven Adler

@sjgadler

2 years

Ok I've seen a lot of awesome DALL-E 2 creations in my time (and certainly today), but this thread is pretty amazing

Nick

@nickcammarata

2 years

dall-e 2 illustrations of my friends' twitter bios

289

929

4K

0

1

5

Steven Adler

@sjgadler

2 years

Some *really* beautiful generations in here, would encourage folks to take a look #dalle

Ben Barry

@benbarry

2 years

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

43

254

1K

0

5

Steven Adler

@sjgadler

2 years

All Too Well (10 Minute Version) (Taylor's Version) ft. #dalle

4

0

5

Steven Adler

@sjgadler

2 years

@mattyglesias "a prosperous and multicultural United States with one billion varied Americans, standing hand-in-hand in loving harmony, high-quality digital art"

0

5

Steven Adler

@sjgadler

1 year

If any of this sounds inspiring, know that we need a ton more people. We'd love to hear from you, especially if you have experience doing right by communities via transformative technology:

0

4

Steven Adler

@sjgadler

2 years

We've nearly tripled how truthful & informative a GPT-3-based system can be on a set of questions specifically designed to be tricky to answer.

Miles Brundage

@Miles_Brundage

2 years

Re-upping this in light of today's WebGPT announcement (). Language models can be steered towards so many tasks beyond "mere" writing (not that that isn't important in itself).

1

3

25

1

5

Steven Adler

@sjgadler

2 years

Not all of these turn out with *great* quality; truthfully, I think I was a little sloppy with the region around the hand, and so sometimes we end up without a guitar at all. But, compared to the version that @ilyasut and I hacked together back in the day, I'll take it!

1

0

5

Steven Adler

@sjgadler

1 year

ChatGPT can even help you clean up the style or organization, if you'd like. You can get the new iPhone app here:

‎ChatGPT

‎Introducing ChatGPT for iOS: OpenAI’s latest advancements at your fingertips. This official app is free, syncs your history across devices, and brings you the newest model improvements from OpenAI....

apps.apple.com

0

4

Steven Adler

@sjgadler

2 years

@rinireg Have you happened to have read @brianchristian 's The Most Human Human? Really excellent book on this topic

1

0

5

Steven Adler

@sjgadler

1 year

And, a link back to the top of the GPT-4 thread for those who've come in part-way:

Steven Adler

@sjgadler

1 year

GPT-4 is officially out! Here are some of the cool things it can do, and some of the mysteries that remain:

2

12

1

0

3

Steven Adler

@sjgadler

1 year

We're still working on a bunch of things - help submit feedback! - but it's great to have such a useful tool for asking questions & improving my understanding. I'm remarkably privileged to have world-class colleagues - and still, ChatGPT is incredibly useful.

arsham

@arshamg_

1 year

During my PhD I spent a lot of time studying a protein called beta-catenin. Today OpenAI released ChatGPT and I asked it a few questions about beta-catenin. LLMs as a learning tool will be incredible. Everyone will have an on-demand socratic method information mentor.

3

0

21

0

4

Steven Adler

@sjgadler

2 years

@_markhudson_ Here's one generated from scratch, and a second I got from Inpainting to one of the classic colorblindness number tests:

0

4

Steven Adler

@sjgadler

2 years

And a further homage to NYC/SF skylines #dalle

0

4

Steven Adler

@sjgadler

1 year

One of the best kept "secrets" at OpenAI: Clicking this button at gets you access to instant, world-class transcription. And now, you can do this at scale with our Whisper API.

Evan Morikawa

@E0M

1 year

Not only did ChatGPT's API release, now Whisper's in the API! Whisper can transcribe audio into text with incredible accuracy. For a sense of scale Alexa gets roughly 1 in 5 words wrong. Whisper in contrast gets close to professional human transcribers

1

4

33

2

1

4

Steven Adler

@sjgadler

2 years

Excited to share some of what we've been working: Tooling to help developers protect against misuse of their applications, and to unlock beneficial uses in sensitive domains, like tutoring for students.

OpenAI

@OpenAI

2 years

Introducing a free new tool that gives OpenAI API developers stronger content moderation abilities

63

142

593

1

0

4

Steven Adler

@sjgadler

2 years

Red (Taylor's Version) ft. #dalle

0

4

Steven Adler

@sjgadler

2 years

I'm not sure I've seen this said elsewhere yet, but JFYI this was on Friday, April 1st - and no, not a joke(!)

0

4

Steven Adler

@sjgadler

2 years

+1 to what Miles said - if you're at all interested in what we're working on, *please* throw in an application; we'd love to hear from you

Miles Brundage

@Miles_Brundage

2 years

Excited about the next phase of our push to bring more folks from underrepresented groups into AI. I have the privilege of working closely with several alums of the earlier iterations of this program and look forward to meeting the next generation!

1

5

37

0

4

Steven Adler

@sjgadler

2 years

@heyhashim @_markhudson_ Truly a wild time for generative art and design

0

4

Steven Adler

@sjgadler

2 years

@ApriiSR @nellfallcard @ESYudkowsky It can! In two ways: what we call Inpainting, and what we call Variations

1

0

4

Steven Adler

@sjgadler

1 year

A nice feature of chat is that you can re-direct GPT if you change your mind, want a variation on the theme, etc. For instance, I redirected it from general 80s upbeat songs to ones with great drum beats: First recommendation: "In the Air Tonight", not bad!

1

0

4

Steven Adler

@sjgadler

2 years

@kshekar @EmilyKager @lauren_n_roth The Gmail is probably their iMessage account - people can choose whether new messages are sent by default from a phone number, email, etc, but many don’t know about this, and even for those who do it can be counterintuitive

0

4

Steven Adler

@sjgadler

2 years

@drawbrandondraw @sloanesloane Good call, much improved:

0

3

Steven Adler

@sjgadler

5 months

@gazorp5 I’m describing how Ilya seemed at our first All-Hands after Sam was fired, before anybody (not even Greg) had resigned

1

0

4

Steven Adler

@sjgadler

2 years

@drawbrandondraw @sloanesloane These are generations for “A black and white cartoon sketch of a robot artist, in the style of Bill Watterson” - my sense is they don’t look a *ton* like his? I bet it would generate good Variations of his work though

2

0

4

Steven Adler

@sjgadler

2 years

@patio11 @sama @patio11 suggest some more and I can jump in too; this system is truly unbelievable, and such a privilege to work on

2

0

4

Steven Adler

@sjgadler

1 year

I remember seeing @sharifshameem ’s wild demos that summer & not believing my eyes - still so far to go

Peter Welinder

@npew

1 year

Around this time 3 years ago, early 2020, we started testing the OpenAI GPT-3 API with the first external users. It was really hard to get anyone to try it, let alone build on it. So much has changed since then, but still feels like we're in the early days.

49

68

962

1

0

3

Steven Adler

@sjgadler

2 years

@rokine40 Yeah that was one of my major things initially too - it still works and is generally more straightforward now :-) for instance, this is just "a 3D rendering of a harp in the shape of a snail"

0

2

Steven Adler

@sjgadler

2 years

Now, to my point - that rightmost image from the beginning isn't *that* great. But one-level more down the tree, look how cool they are! It's DALL-E images all the way down.

1

0

3

Steven Adler

@sjgadler

2 years

When I see impressive artwork in my Twitter feed, I'm now often checking the bottom-right for our "DALL-E signature" to see if it was AI-generated. DALL-E has seriously changed the way I interact with media online & what I believe to be possible.

0

3

Steven Adler

@sjgadler

2 years

It's awesome to see this level of curation & creativity - a great communal resource for folks getting started with #dalle

Guy Parsons

@GuyP

2 years

It's here: the ✨ #DALLE Prompt Book ✨, first edition! Free to download, it features 82 pages of artistic inspiration with over 300 examples of #DALLE2 images! Here's what's inside... 🧵

162

700

4K

1

0

3

Steven Adler

@sjgadler

2 years

@tejasdkulkarni @OpenAI ^prompted with "'{the above}', digital art"

0

3

Steven Adler

@sjgadler

2 years

@ashwinsyammusic

1

0

3