Researchers asked an AI model to draw “an avocado armchair.” The results show how we might make artificial intelligence smarter. https://t.co/xaNEHrDHcl

— MIT Technology Review (@techreview) January 6, 2021

RIP stock photography https://t.co/XJ6lHYkCeE pic.twitter.com/RRhAc2AdN9

— Caleb Watney (@calebwatney) January 5, 2021

Consider this your notice, if you're a manga artist: you have N years left before you're out of a job. I wish that I had any grasp whatsoever how to relate N to announcements like these. My initial sense is N=2, wisely adjusted upwards to "actually after the end of the world". https://t.co/HXRV4ygbGO

— Eliezer Yudkowsky (@ESYudkowsky) January 6, 2021

And, for fun, generated images of "an illustration of a baby shark in a wizard hat wielding a blue light saber".

(You can try other combinations here: https://t.co/aOIbGLSYm7) pic.twitter.com/o2Q2yfMSIB

— Sam Altman (@sama) January 5, 2021

An NN takes a list of category names, and outputs (in a zero-shot manner) a visual classifier.

It beats RN50 on ImageNet zero-shot, while being far more robust to unusual images:https://t.co/dGdtFlbI7G pic.twitter.com/tjYdMfFcfe

— Ilya Sutskever (@ilyasut) January 5, 2021

This is worth a close look for *anybody* curious about the future. So many creative processes stand to be changed. https://t.co/ZSFWjQqknR

— Kanyi Maqubela (@km) January 5, 2021

CLIP — our new neural network for classifying images into categories based on arbitrary text.

Works like GPT-3's semantic search, but for images: https://t.co/T4Jx4keGvM

Maybe a path towards vision nets that don't make silly mistakes:https://t.co/Fixj02nrPd pic.twitter.com/D0Q5ue0XNo

— Greg Brockman (@gdb) January 5, 2021

How long until twitter's little GIF widget actually generates the GIFs? I'm sick of no good results for "Exasperated and tired dachshund wearing red bowtie and pointing emphatically at text of 47 U.S.C. § 230." https://t.co/nGOfnbfdU5

— Neil Chilson (@neil_chilson) January 5, 2021

“DALL·E is the kind of system that Riedl imagined submitting to the Lovelace 2.0 test, a thought experiment... for measuring artificial intelligence. It assumes that one mark of intelligence is the ability to blend concepts in creative ways.” https://t.co/39vEGt3XXq

— Mark O. Riedl (@mark_riedl) January 6, 2021

People think AI is coming for truck drivers first? Boy do i have news for you... https://t.co/X6VkocDCIU

— Daniel ⚡️ (@danielrakh) January 5, 2021

What's the future of creativity and intellectual property rights if an AI model generates the next chair design?https://t.co/j9ejPPTXPW

— Jonathan Berte (@jonathanberte) January 5, 2021

We on Google Photos spend a lot of time on the inverse of this, and I’ll say, this is quite impressive. https://t.co/x8tGQor9Zv

— David Lieb (@dflieb) January 5, 2021

oh yes, evil boba ??https://t.co/1fi0TxK9zU pic.twitter.com/b02gzivW8E

— Jane Manchun Wong (@wongmjane) January 6, 2021

I was going to show a few more examples but honestly it's just worth 5 minutes of your time to go play around with different combinations: https://t.co/aOIbGLSYm7

— Sam Altman (@sama) January 5, 2021

... i wanna get into this and see if it'll write assessment reports for me.

but im gonna start with using it to do all the slides for my next con talk, which will be

"how to vet your security vendors" https://t.co/buXSycrwgf

— D̒͂̕ᵈăᵃn̕ᶰ Ť̾̾̓͐͒͠ᵗe͗̑́̋̂́͡ᵉn̅ᶰtᵗl̀̓͘ᶫe̓̒̂̚ᵉrʳ (@Viss) January 5, 2021

I, for one, am looking forward to the copyright lawsuits over who holds the copyright for these images (in many cases the answer should be "no one, they're public domain"). https://t.co/ML4Hwz7z8m

— Mike Masnick (@mmasnick) January 5, 2021

They deliberately castrated this tool so people wouldn't use it to make porn https://t.co/Hi6piikzAF

— Humans of ____ (@HumansOfFlat) January 5, 2021

They limited the possible inputs to this tool out of fear of what it could show you. Its generative capacity is limitless, infinite, obscene. You can ask it for anything

Abby Shapiro's nudes. The true face of any anon. A picture of your future wife. The girl reading this. https://t.co/XjOIhkYsV2

— Zero HP Lovecraft (@0x49fa98) January 5, 2021

Wow - this AI can now generate unique images *entirely* from text prompts. Impressive, although somewhat disappointed the available prompts are so... vanilla.
Also GG, illustrators https://t.co/awQ0XqB8vB

— Liv Boeree (@Liv_Boeree) January 5, 2021

Tag yourself. I'm Gamer Avo Chair second row, second from left. I'm staying the hell away from Giant Pit Avo Chair bottom row middle https://t.co/Bpxuex88Ly pic.twitter.com/JCx0kOteM7

— Liam Dillon (@dillonliam) January 6, 2021

humans had a good run https://t.co/Z8f3ollnH5

— Adam Ludwin (@adamludwin) January 5, 2021

I've gently suggested that this sort of technology will make many of the current startup ideas I see being pitched completely obsolete. Follow this closely. https://t.co/vvgujukLJ4

— Del Johnson (@DelJohnsonVC) January 5, 2021

This is absolutely mind melting. Open AI can generate nearly unlimited images of a chair that looks like an avocado.https://t.co/EYMiRNEyPd

— Fraser Cain (@fcain) January 6, 2021

DALL-E is an incredible leap from @OpenAI. For @newscientist I dug into what's going on https://t.co/gpSqz6Iav4

— Chris Stokel-Walker (@stokel) January 5, 2021

AI illustrator draws imaginative pictures to go with text captions - New Scientist News #AI #DigitalTransformation CC:@AI_bulletin https://t.co/9LXpLSsRD4

— ????????????４??? (@digital_trans4m) January 6, 2021

#AI illustrator draws imaginative pictures to go with text captions.
By @newscientist #OpenAI #NeuralNetworks #Tech #CES2021 #ArtificialIntelligence
Cc: @jdelacruzphi @gerald_bader@PawlowskiMario @FmFrancoise @AlbertoEMachado @Nicochan33 @jblefevre60https://t.co/2lwN3XwfJu pic.twitter.com/Q9yew1ti1y

— Fabrizio Bustamante #CES2021 (@Fabriziobustama) January 6, 2021

“The real test is seeing how far the #AI can be pushed outside its comfort zone,” @mark_riedl https://t.co/BA8YpD2005

— Georgia Tech Computing (@gtcomputing) January 6, 2021

This avocado #armchair

could be the #future of #AI https://t.co/6ObSTsNuib #fintech #ArtificialIntelligence #MachineLearning #DeepLeanring @strwbilly @techreview @OpenAI @psb_dc @ImMBM @Paula_Piccard @Fisher85M @Damien_CABADI @mvollmer1 @enricomolinari @antgrasso pic.twitter.com/Vkce5VYMPf

— Spiros Margaris (@SpirosMargaris) January 6, 2021

So it will be able to write your content & create images for it too. Oh boy :) -> OpenAI introduces two new GPT-3 models: CLIP, which classifies images into categories from arbitrary text, and DALL·E, which can generate images from text https://t.co/Ki7OYNxbMU pic.twitter.com/K4lq9wmvK6

— Glenn Gabe (@glenngabe) January 6, 2021

This avocado armchair could be the future of AI - by @strwbilly via @techreview https://t.co/QYpDYXjjeJ #AI #DL #GPT3 #DALLE #CLIP #TextToPixels @OpenAI
cc @antgrasso @Nicochan33 @nigewillson @tlloydjones @gerald_bader @WhiteheartVic @RealRavi__ @RLDI_Lamy @Analytics_699

— BusinessIntelligence (@bimedotcom) January 6, 2021

This avocado armchair could be the future of #AI #futureofwork #CES2021 #openai #gpt3 #DeepLearning#ML #MachineLearning#100DaysOfCode #100DaysOfMLCode@PawlowskiMario @MargaretSiegienhttps://t.co/IFv7fBM98Z

— Margaret Siegien ? ??#CES2021 (@MargaretSiegien) January 6, 2021

This avocado armchair could be the #future of #AI #ArtificialIntelligence #imageRecognition #Algorithm #GPT3 #NLP #NaturalLanguageProcessing #ML #MachineLearning #DeepLearning #DL #Data #Tech #Technologyhttps://t.co/pkUZi8Lvqp pic.twitter.com/3AzM2COxpF

— Andres Vilariño (@andresvilarino) January 6, 2021

OpenAI's new machine learning AI model generates images from text
What GPT-3 did for text, DALL-E is aiming to do for images #ai #MachineLearning #DataScience #100DaysOfCodehttps://t.co/Ga0pzEbUXK pic.twitter.com/VI199SlojO

— La Forge AI (@LaForge_AI) January 6, 2021

A new AI model draws images from text#100DaysOfCode #100DaysOfMLCode #DEVCommunity #womenwhocode #javascript #Serverless #ArtificialIntelligence #MachineLearning #AI #DeepLearning #MLhttps://t.co/pCs86pgDnR

— Ravi (@RealRavi__) January 6, 2021

A new AI model draws images from text https://t.co/4AYOryK01g #MachineLearning #DataScience #AI #100DaysOfCode #DEVCommunity #IoT #flutter #javascript #womenintech #CyberSecurity #RStats #CodeNewbie #datasecurity #data #WomenWhoCode #tech #Digital #NeuralNetworks #gpt3 #openai

— Rimah Harb (@HarbRimah) January 6, 2021

OpenAI's new model can draw images from a written description https://t.co/UF4nUfTMg1 @axios via @enricomolinari #fintech #finserv #AI #insurtech #proptech #ML@mirko_ross @CelineDarnet @craigiskowitz @aldoceccarelli @JeroenBartelse @drsharwood @MS1MN @intellimetri @interfima

— ? Enrico Molinari #FinTech ?????? #CES2021 (@enricomolinari) January 6, 2021

#OpenAI's new model can draw images from a written description#AI #ML #MachineLearning#ArtificialIntelligence #gpt3#DeepLearning #100DaysOfCode#100DaysOfMLCode #CES2021@MargaretSiegien @PawlowskiMario https://t.co/8y2qzWHf7i

— Margaret Siegien ? ??#CES2021 (@MargaretSiegien) January 6, 2021

#OpenAI release #DALL-E, an #AI model that can draw a coherent image from a text description. We're getting closer to general intelligence! #machinelearning #artificialintelligence https://t.co/hHFE65iy88

— Zeek? (@MonikaVenck) January 6, 2021

https://t.co/gmYHvKfCwv
Very Interesting
The machine learning company OpenAI is developing models that improve computer vision and can produce original images from a text prompt.#AI #ArtificialIntelligence @OpenAI #MachineLearning

— Hamid Taebi (@HamidTaebi) January 6, 2021

Future of Design ?
This avocado armchair could be the future of Artificial Intelligence https://t.co/PoxONwvACH #ai #artificalintelligence #machinelearning #deeplearning #design #creativity #gpt3 pic.twitter.com/gwjtlpo8p4

— Nige Willson (@nigewillson) January 7, 2021

#naturallanguageprocessing #Artificialintelligence@OpenAI has extended #GPT3 with two new models that combine #NLP with image recognition to give its #AI a better understanding of everyday concepts.

by @techreview
ty @_SalimHouarihttps://t.co/PzqLreSiNG

— SwissCognitive – The Global AI Hub (@SwissCognitive) January 7, 2021

OpenAI has built two new models, called DALL·E and CLIP, that combine language and images in a way that will make AIs better at understanding both words and what they refer to.. https://t.co/vPAW3wg5v0

— Xaret (@xaret_) January 6, 2021

Could this #avocado armchair be the future of #AI?#OpenAI has extended #GPT-3 with two new models that combine #NLP with image recognition to give its AI a better understanding of everyday concepts. https://t.co/7jyGlfl03i via @techreview pic.twitter.com/VwcBfnX5Td

— Helen Yu (@YuHelenYu) January 7, 2021

OpenAI has extended GPT-3 with two new models that combine NLP with image recognition to give its #AI a better understanding of everyday concepts. https://t.co/7n6yZ4iwE0

— Exponential Medicine (@ExponentialMed) January 7, 2021

This avocado #armchair could be the future of #AI .@Hana_ElSayyed @GlenGilmore @MargaretSiegien @RitupaGhosh@AngelikaLattner @ShiCooks@AilsaForshaw @fogle_shane@AmitChampaneri1https://t.co/c33vSPCIzl

— Abhishek Yadav (@abhishek__AI) January 7, 2021

This avocado armchair could be the future of AIhttps://t.co/d0G4aPMl3p pic.twitter.com/o3169Pd0lv

— Lalo Zanoni (@zanoni) January 6, 2021

OpenAI's new machine learning AI model generates images from text

OpenAI is developing models that improve computer vision and can produce original images from a text prompt#AI #MachineLearning #GPT3 #DALLE #CLIP #OpenAI by Bryan Walsh / @Axios https://t.co/hoc5Hp3WKK

— Robert Zembowicz (@rzembo) January 7, 2021

New #AI model can create images based on simple text! https://t.co/C6nzGzB08n

— Alexandre Glas (@Alexandre_Glas) January 6, 2021

A radish in a tutu walking a dog!! I want my home wrapped in this wallpaper by ⁦@OpenAI⁩’s latest marvel #DALLE: these are original images generated by a new #AI model displaying features of genuine #originality, dare I say, #creativity?. #art #ml https://t.co/bDuPoEJnQO

— Clara Blume (@clara_blume) January 6, 2021