Did Gunnar Larson, rape Mr. Mark Zuckerburg? Or, was it fair game?
   Finders keepers?

   On Fri, Apr 8, 2022, 7:56 PM <[1]cypherpunks-request@lists.cpunks.org>
   wrote:

     Send cypherpunks mailing list submissions to
             [2]cypherpunks@lists.cpunks.org
     To subscribe or unsubscribe via the World Wide Web, visit
             [3]https://lists.cpunks.org/mailman/listinfo/cypherpunks
     or, via email, send a message with subject or body 'help' to
             [4]cypherpunks-request@lists.cpunks.org
     You can reach the person managing the list at
             [5]cypherpunks-owner@lists.cpunks.org
     When replying, please edit your Subject line so it is more specific
     than "Re: Contents of cypherpunks digest..."
     Today's Topics:
        1. Re: cypherpunks Digest, Vol 106, Issue 93 (Gunnar Larson)
     --------------------------------------------------------------------
     --
     Message: 1
     Date: Fri, 8 Apr 2022 19:54:15 -0400
     From: Gunnar Larson <[6]g@xny.io>
     To: cypherpunks <[7]cypherpunks@lists.cpunks.org>
     Subject: Re: cypherpunks Digest, Vol 106, Issue 93
     Message-ID:

     <CAPc8xwPsCK2cA3tT1U-wjuV09T5kc=[8]TBMcrzLz46uyNHJXV9cg@mail.gmail.c
     om>
     Content-Type: text/plain; charset="utf-8"
     At first glance, this was a great article.
     On Fri, Apr 8, 2022, 7:52 PM
     <[9]cypherpunks-request@lists.cpunks.org> wrote:
     > Send cypherpunks mailing list submissions to
     >         [10]cypherpunks@lists.cpunks.org
     >
     > To subscribe or unsubscribe via the World Wide Web, visit
     >         [11]https://lists.cpunks.org/mailman/listinfo/cypherpunks
     > or, via email, send a message with subject or body 'help' to
     >         [12]cypherpunks-request@lists.cpunks.org
     >
     > You can reach the person managing the list at
     >         [13]cypherpunks-owner@lists.cpunks.org
     >
     > When replying, please edit your Subject line so it is more
     specific
     > than "Re: Contents of cypherpunks digest..."
     >
     >
     > Today's Topics:
     >
     >    1. Re: DALL-E (coderman)
     >
     >
     >
     --------------------------------------------------------------------
     --
     >
     > Message: 1
     > Date: Fri, 08 Apr 2022 23:50:53 +0000
     > From: coderman <[14]coderman@protonmail.com>
     > To: coderman <[15]coderman@protonmail.com>
     > Cc: "cy\"Cypherpunks" <[16]cypherpunks@cpunks.org>
     > Subject: Re: DALL-E
     > Message-ID:
     >
     >
     <a9WeFGpr9g422W0Uym9aQZyxT6mqWNzNwLsG6yKqqlD4BLpH6NxuARXLOMvBY8IdZF9
     HMetBKZYGjdH--qJRFZDIWnXdMRQVqr3pmMYVo5I=@
     > [17]protonmail.com>
     >
     > Content-Type: text/plain; charset="utf-8"
     >
     > DALL·E[1]([18]https://openai.com/blog/dall-e/#fn1)
     >
     > We decided to name our model using a portmanteau of the artist
     Salvador
     > Dalí and Pixar’s WALL·E.
     >
     > is a 12-billion parameter version of[GPT-3](
     > [19]https://arxiv.org/abs/2005.14165) trained to generate images
     from text
     > descriptions, using a dataset of text–image pairs. We’ve found
     that it has
     > a diverse set of capabilities, including creating
     anthropomorphized
     > versions of animals and objects, combining unrelated concepts in
     plausible
     > ways, rendering text, and applying transformations to existing
     images.
     >
     > ---------------------------------------------------------------
     >
     > Text prompt
     > an illustration of a baby daikon radish in a tutu walking a dog
     > AI-generated
     > images
     >
     > Edit prompt or view more images
     > Text prompt
     > an armchair in the shape of an avocado. . . .
     > AI-generated
     > images
     >
     > Edit prompt or view more images
     > Text prompt
     > a store front that has the word ‘openai’ written on it. . . .
     > AI-generated
     > images
     >
     > Edit prompt or view more images
     > Text & image
     > prompt
     > the exact same cat on the top as a sketch on the bottom
     > AI-generated
     > images
     >
     > Edit prompt or view more images
     > ---------------------------------------------------------------
     >
     > GPT-3 showed that language can be used to instruct a large neural
     network
     > to perform a variety of text generation tasks. [Image GPT](
     > [20]https://openai.com/blog/image-gpt) showed that the same type
     of neural
     > network can also be used to generate images with high fidelity. We
     extend
     > these findings to show that manipulating visual concepts through
     language
     > is now within reach.
     >
     > Overview
     >
     > Like GPT-3, DALL·E is a transformer language model. It receives
     both the
     > text and the image as a single stream of data containing up to
     1280 tokens,
     > and is trained using maximum likelihood to generate all of the
     tokens, one
     > after another.[2]([21]https://openai.com/blog/dall-e/#fn2)
     >
     > A token is any symbol from a discrete vocabulary; for humans, each
     English
     > letter is a token from a 26-letter alphabet. DALL·E’s vocabulary
     has tokens
     > for both text and image concepts. Specifically, each image caption
     is
     > represented using a maximum of 256 BPE-encoded tokens with a
     vocabulary
     > size of 16384, and the image is represented using 1024 tokens with
     a
     > vocabulary size of 8192.
     >
     > The images are preprocessed to 256x256 resolution during training.
     Similar
     > to VQVAE,[14](
     >
     [22]https://openai.com/blog/dall-e/#rf14)[15](https://openai.com/blo
     g/dall-e/#rf15)
     > each image is compressed to a 32x32 grid of discrete latent codes
     using a
     > discrete VAE[10](
     >
     [23]https://openai.com/blog/dall-e/#rf10)[11](https://openai.com/blo
     g/dall-e/#rf11)
     > that we pretrained using a continuous relaxation.[12](
     >
     [24]https://openai.com/blog/dall-e/#rf12)[13](https://openai.com/blo
     g/dall-e/#rf13)
     > We found that training using the relaxation obviates the need for
     an
     > explicit codebook, EMA loss, or tricks like dead code revival, and
     can
     > scale up to large vocabulary sizes.
     >
     > This training procedure allows DALL·E to not only generate an
     image from
     > scratch, but also to regenerate any rectangular region of an
     existing image
     > that extends to the bottom-right corner, in a way that is
     consistent with
     > the text prompt.
     >
     > We recognize that work involving generative models has the
     potential for
     > significant, broad societal impacts. In the future, we plan to
     analyze how
     > models like DALL·E relate to societal issues like economic impact
     on
     > certain work processes and professions, the potential for bias in
     the model
     > outputs, and the longer term ethical challenges implied by this
     technology.
     >
     > Capabilities
     >
     > We find that DALL·E is able to create plausible images for a great
     variety
     > of sentences that explore the compositional structure of language.
     We
     > illustrate this using a series of interactive visuals in the next
     section.
     > The samples shown for each caption in the visuals are obtained by
     taking
     > the top 32 of 512 after reranking with [CLIP](
     > [25]https://openai.com/blog/clip/), but we do not use any manual
     > cherry-picking, aside from the thumbnails and standalone images
     that appear
     > outside.[3]([26]https://openai.com/blog/dall-e/#fn3)
     >
     > Further details provided in [a later section](
     > [27]https://openai.com/blog/dall-e/#summary).
     >
     > Controlling Attributes
     >
     > We test DALL·E’s ability to modify several of an object’s
     attributes, as
     > well as the number of times that it appears.
     >
     > Click to edit text prompt or view more AI-generated images
     > a pentagonal green clock. a green clock in the shape of a
     pentagon.
     >
     > navigatedownwide
     > a cube made of porcupine. a cube with the texture of a porcupine.
     >
     > navigatedownwide
     > a collection of glasses is sitting on a table
     >
     > navigatedownwide
     >
     > Drawing Multiple Objects
     >
     > Simultaneously controlling multiple objects, their attributes, and
     their
     > spatial relationships presents a new challenge. For example,
     consider the
     > phrase “a hedgehog wearing a red hat, yellow gloves, blue shirt,
     and green
     > pants.” To correctly interpret this sentence, DALL·E must not only
     > correctly compose each piece of apparel with the animal, but also
     form the
     > associations (hat, red), (gloves, yellow), (shirt, blue), and
     (pants,
     > green) without mixing them
     up.[4]([28]https://openai.com/blog/dall-e/#fn4)
     >
     > This task is called variable binding, and has been extensively
     studied in
     > the literature.[17](
     >
     [29]https://openai.com/blog/dall-e/#rf17)[18](https://openai.com/blo
     g/dall-e/#rf18)[19](https://openai.com/blog/dall-e/#rf19)[20](https:
     //openai.com/blog/dall-e/#rf20
     > )
     >
     > We test DALL·E’s ability to do this for relative positioning,
     stacking
     > objects, and controlling multiple attributes.
     >
     > a small red block sitting on a large green block
     >
     > navigatedownwide
     > a stack of 3 cubes. a red cube is on the top, sitting on a green
     cube. the
     > green cube is in the middle, sitting on a blue cube. the blue cube
     is on
     > the bottom.
     >
     > navigatedownwide
     > an emoji of a baby penguin wearing a blue hat, red gloves, green
     shirt,
     > and yellow pants
     >
     > navigatedownwide
     >
     > While DALL·E does offer some level of controllability over the
     attributes
     > and positions of a small number of objects, the success rate can
     depend on
     > how the caption is phrased. As more objects are introduced, DALL·E
     is prone
     > to confusing the associations between the objects and their
     colors, and the
     > success rate decreases sharply. We also note that DALL·E is
     brittle with
     > respect to rephrasing of the caption in these scenarios:
     alternative,
     > semantically equivalent captions often yield no correct
     interpretations.
     >
     > Visualizing Perspective and Three-Dimensionality
     >
     > We find that DALL·E also allows for control over the viewpoint of
     a scene
     > and the 3D style in which a scene is rendered.
     >
     > an extreme close-up view of a capybara sitting in a field
     >
     > navigatedownwide
     > a capybara made of voxels sitting in a field
     >
     > navigatedownwide
     >
     > To push this further, we test DALL·E’s ability to repeatedly draw
     the head
     > of a well-known figure at each angle from a sequence of equally
     spaced
     > angles, and find that we can recover a smooth animation of the
     rotating
     > head.
     >
     > a photograph of a bust of homer
     >
     > navigatedownwide
     >
     > DALL·E appears to be able to apply some types of optical
     distortions to
     > scenes, as we see with the options “fisheye lens view” and “a
     spherical
     > panorama.” This motivated us to explore its ability to generate
     reflections.
     >
     > a plain white cube looking at its own reflection in a mirror. a
     plain
     > white cube gazing at itself in a mirror.
     >
     > navigatedownwide
     >
     > Visualizing Internal and External Structure
     >
     > The samples from the “extreme close-up view” and “x-ray” style led
     us to
     > further explore DALL·E’s ability to render internal structure with
     > cross-sectional views, and external structure with macro
     photographs.
     >
     > a cross-section view of a walnut
     >
     > navigatedownwide
     > a macro photograph of brain coral
     >
     > navigatedownwide
     >
     > Inferring Contextual Details
     >
     > The task of translating text to images is underspecified: a single
     caption
     > generally corresponds to an infinitude of plausible images, so the
     image is
     > not uniquely determined. For instance, consider the caption “a
     painting of
     > a capybara sitting on a field at sunrise.” Depending on the
     orientation of
     > the capybara, it may be necessary to draw a shadow, though this
     detail is
     > never mentioned explicitly. We explore DALL·E’s ability to resolve
     > underspecification in three cases: changing style, setting, and
     time;
     > drawing the same object in a variety of different situations; and
     > generating an image of an object with specific text written on it.
     >
     > a painting of a capybara sitting in a field at sunrise
     >
     > navigatedownwide
     > a stained glass window with an image of a blue strawberry
     >
     > navigatedownwide
     > a store front that has the word ‘openai’ written on it. a store
     front that
     > has the word ‘openai’ written on it. a store front that has the
     word
     > ‘openai’ written on it. ‘openai’ store front.
     >
     > navigatedownwide
     >
     > With varying degrees of reliability, DALL·E provides access to a
     subset of
     > the capabilities of a 3D rendering engine via natural language. It
     can
     > independently control the attributes of a small number of objects,
     and to a
     > limited extent, how many there are, and how they are arranged with
     respect
     > to one another. It can also control the location and angle from
     which a
     > scene is rendered, and can generate known objects in compliance
     with
     > precise specifications of angle and lighting conditions.
     >
     > Unlike a 3D rendering engine, whose inputs must be specified
     unambiguously
     > and in complete detail, DALL·E is often able to “fill in the
     blanks” when
     > the caption implies that the image must contain a certain detail
     that is
     > not explicitly stated.
     >
     > Applications of Preceding Capabilities
     >
     > Next, we explore the use of the preceding capabilities for fashion
     and
     > interior design.
     >
     > a male mannequin dressed in an orange and black flannel shirt
     >
     > navigatedownwide
     > a female mannequin dressed in a black leather jacket and gold
     pleated skirt
     >
     > navigatedownwide
     > a living room with two white armchairs and a painting of the
     colosseum.
     > the painting is mounted above a modern fireplace.
     >
     > navigatedownwide
     > a loft bedroom with a white bed next to a nightstand. there is a
     fish tank
     > beside the bed.
     >
     > navigatedownwide
     >
     > Combining Unrelated Concepts
     >
     > The compositional nature of language allows us to put together
     concepts to
     > describe both real and imaginary things. We find that DALL·E also
     has the
     > ability to combine disparate ideas to synthesize objects, some of
     which are
     > unlikely to exist in the real world. We explore this ability in
     two
     > instances: transferring qualities from various concepts to
     animals, and
     > designing products by taking inspiration from unrelated concepts.
     >
     > a snail made of harp. a snail with the texture of a harp.
     >
     > navigatedownwide
     > an armchair in the shape of an avocado. an armchair imitating an
     avocado.
     >
     > navigatedownwide
     >
     > Animal Illustrations
     >
     > In the previous section, we explored DALL·E’s ability to combine
     unrelated
     > concepts when generating images of real-world objects. Here, we
     explore
     > this ability in the context of art, for three kinds of
     illustrations:
     > anthropomorphized versions of animals and objects, animal
     chimeras, and
     > emojis.
     >
     > an illustration of a baby daikon radish in a tutu walking a dog
     >
     > navigatedownwide
     > a professional high quality illustration of a giraffe turtle
     chimera. a
     > giraffe imitating a turtle. a giraffe made of turtle.
     >
     > navigatedownwide
     > a professional high quality emoji of a lovestruck cup of boba
     >
     > navigatedownwide
     >
     > Zero-Shot Visual Reasoning
     >
     > GPT-3 can be instructed to perform many kinds of tasks solely from
     a
     > description and a cue to generate the answer supplied in its
     prompt,
     > without any additional training. For example, when prompted with
     the phrase
     > “here is the sentence ‘a person walking his dog in the park’
     translated
     > into French:”, GPT-3 answers “un homme qui promène son chien dans
     le parc.”
     > This capability is called zero-shot reasoning. We find that DALL·E
     extends
     > this capability to the visual domain, and is able to perform
     several kinds
     > of image-to-image translation tasks when prompted in the right
     way.
     >
     > the exact same cat on the top as a sketch on the bottom
     >
     > navigatedownwide
     > the exact same teapot on the top with ’gpt’ written on it on the
     bottom
     >
     > navigatedownwide
     >
     > We did not anticipate that this capability would emerge, and made
     no
     > modifications to the neural network or training procedure to
     encourage it.
     > Motivated by these results, we measure DALL·E’s aptitude for
     analogical
     > reasoning problems by testing it on Raven’s progressive matrices,
     a visual
     > IQ test that saw widespread use in the 20th century.
     >
     > a sequence of geometric shapes.
     >
     > navigatedownwide
     >
     > Geographic Knowledge
     >
     > We find that DALL·E has learned about geographic facts, landmarks,
     and
     > neighborhoods. Its knowledge of these concepts is surprisingly
     precise in
     > some ways and flawed in others.
     >
     > a photo of the food of china
     >
     > navigatedownwide
     > a photo of alamo square, san francisco, from a street at night
     >
     > navigatedownwide
     > a photo of san francisco’s golden gate bridge
     >
     > navigatedownwide
     >
     > Temporal Knowledge
     >
     > In addition to exploring DALL·E’s knowledge of concepts that vary
     over
     > space, we also explore its knowledge of concepts that vary over
     time.
     >
     > a photo of a phone from the 20s
     >
     > navigatedownwide
     >
     > Summary of Approach and Prior Work
     >
     > DALL·E is a simple decoder-only transformer that receives both the
     text
     > and the image as a single stream of 1280 tokens—256 for the text
     and 1024
     > for the image—and models all of them autoregressively. The
     attention mask
     > at each of its 64 self-attention layers allows each image token to
     attend
     > to all text tokens. DALL·E uses the standard causal mask for the
     text
     > tokens, and sparse attention for the image tokens with either a
     row,
     > column, or convolutional attention pattern, depending on the
     layer. We
     > provide more details about the architecture and training procedure
     in our
     > [paper]([30]https://arxiv.org/abs/2102.12092).
     >
     > Text-to-image synthesis has been an active area of research since
     the
     > pioneering work of Reed et.
     al,[1]([31]https://openai.com/blog/dall-e/#rf1)
     > whose approach uses a GAN conditioned on text embeddings. The
     embeddings
     > are produced by an encoder pretrained using a contrastive loss,
     not unlike
     > CLIP. StackGAN[3]([32]https://openai.com/blog/dall-e/#rf3) and
     StackGAN++[4](
     > [33]https://openai.com/blog/dall-e/#rf4) use multi-scale GANs to
     scale up the
     > image resolution and improve visual fidelity. AttnGAN[5](
     > [34]https://openai.com/blog/dall-e/#rf5) incorporates attention
     between the
     > text and image features, and proposes a contrastive text-image
     feature
     > matching loss as an auxiliary objective. This is interesting to
     compare to
     > our reranking with CLIP, which is done offline. Other work[2](
     >
     [35]https://openai.com/blog/dall-e/#rf2)[6](https://openai.com/blog/
     dall-e/#rf6)[7](https://openai.com/blog/dall-e/#rf7)
     > incorporates additional sources of supervision during training to
     improve
     > image quality. Finally, work by Nguyen et. al[8](
     > [36]https://openai.com/blog/dall-e/#rf8) and Cho et. al[9](
     > [37]https://openai.com/blog/dall-e/#rf9) explores sampling-based
     strategies
     > for image generation that leverage pretrained multimodal
     discriminative
     > models.
     >
     > Similar to the rejection sampling used in [VQVAE-2](
     > [38]https://arxiv.org/abs/1906.00446), we use [CLIP](
     > [39]https://openai.com/blog/clip/) to rerank the top 32 of 512
     samples for
     > each caption in all of the interactive visuals. This procedure can
     also be
     > seen as a kind of language-guided search[16](
     > [40]https://openai.com/blog/dall-e/#rf16), and can have a dramatic
     impact on
     > sample quality.
     >
     > an illustration of a baby daikon radish in a tutu walking a dog
     [caption
     > 1, best 8 of 2048]
     >
     >
     >
     navigatedownwide----------------------------------------------------
     -----------
     >
     > Footnotes
     >
     > -
     >
     > We decided to name our model using a portmanteau of the artist
     Salvador
     > Dalí and Pixar’s WALL·E.
     [↩︎]([41]https://openai.com/blog/dall-e/#fnref1)
     >
     > -
     >
     > A token is any symbol from a discrete vocabulary; for humans, each
     English
     > letter is a token from a 26-letter alphabet. DALL·E’s vocabulary
     has tokens
     > for both text and image concepts. Specifically, each image caption
     is
     > represented using a maximum of 256 BPE-encoded tokens with a
     vocabulary
     > size of 16384, and the image is represented using 1024 tokens with
     a
     > vocabulary size of 8192.
     >
     > The images are preprocessed to 256x256 resolution during training.
     Similar
     > to VQVAE,[14](
     >
     [42]https://openai.com/blog/dall-e/#rf14)[15](https://openai.com/blo
     g/dall-e/#rf15)
     > each image is compressed to a 32x32 grid of discrete latent codes
     using a
     > discrete VAE[10](
     >
     [43]https://openai.com/blog/dall-e/#rf10)[11](https://openai.com/blo
     g/dall-e/#rf11)
     > that we pretrained using a continuous relaxation.[12](
     >
     [44]https://openai.com/blog/dall-e/#rf12)[13](https://openai.com/blo
     g/dall-e/#rf13)
     > We found that training using the relaxation obviates the need for
     an
     > explicit codebook, EMA loss, or tricks like dead code revival, and
     can
     > scale up to large vocabulary sizes. [↩︎](
     > [45]https://openai.com/blog/dall-e/#fnref2)
     >
     > -
     >
     > Further details provided in [a later section](
     > [46]https://openai.com/blog/dall-e/#summary). [↩︎](
     > [47]https://openai.com/blog/dall-e/#fnref3)
     >
     > -
     >
     > This task is called variable binding, and has been extensively
     studied in
     > the literature.[17](
     >
     [48]https://openai.com/blog/dall-e/#rf17)[18](https://openai.com/blo
     g/dall-e/#rf18)[19](https://openai.com/blog/dall-e/#rf19)[20](https:
     //openai.com/blog/dall-e/#rf20)
     > [↩︎]([49]https://openai.com/blog/dall-e/#fnref4)
     >
     > ---------------------------------------------------------------
     >
     > References
     >
     > - Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee,
     H.
     > (2016). “[Generative adversarial text to image synthesis](
     > [50]https://arxiv.org/abs/1605.05396)”. In ICML 2016. [↩︎](
     > [51]https://openai.com/blog/dall-e/#rfref1)
     >
     > - Reed, S., Akata, Z., Mohan, S., Tenka, S., Schiele, B., Lee, H.
     (2016).
     > “[Learning what and where to
     draw]([52]https://arxiv.org/abs/1610.02454)”. In
     > NIPS 2016. [↩︎]([53]https://openai.com/blog/dall-e/#rfref2)
     >
     > - Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang X.,
     Metaxas, D.
     > (2016). “[StackGAN: Text to photo-realistic image synthesis with
     stacked
     > generative adversarial
     networks]([54]https://arxiv.org/abs/1612.03242)”. In
     > ICCY 2017. [↩︎]([55]https://openai.com/blog/dall-e/#rfref3)
     >
     > - Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X.,
     Metaxas, D.
     > (2017). “[StackGAN++: realistic image synthesis with stacked
     generative
     > adversarial networks]([56]https://arxiv.org/abs/1710.10916)”. In
     IEEE TPAMI
     > 2018. [↩︎]([57]https://openai.com/blog/dall-e/#rfref4)
     >
     > - Xu, T., Zhang, P., Huang, Q., Zhang, H., Gan, Z., Huang, X., He,
     X.
     > (2017). “[AttnGAN: Fine-grained text to image generation with
     attentional
     > generative adversarial
     networks]([58]https://arxiv.org/abs/1711.10485). [↩︎](
     > [59]https://openai.com/blog/dall-e/#rfref5)
     >
     > - Li, W., Zhang, P., Zhang, L., Huang, Q., He, X., Lyu, S., Gao,
     J.
     > (2019). “[Object-driven text-to-image synthesis via adversarial
     training](
     > [60]https://arxiv.org/abs/1902.10740)”. In CVPR 2019. [↩︎](
     > [61]https://openai.com/blog/dall-e/#rfref6)
     >
     > - Koh, J. Y., Baldridge, J., Lee, H., Yang, Y. (2020).
     “[Text-to-image
     > generation grounded by fine-grained user attention](
     > [62]https://arxiv.org/abs/2011.03775)”. In WACV 2021. [↩︎](
     > [63]https://openai.com/blog/dall-e/#rfref7)
     >
     > - Nguyen, A., Clune, J., Bengio, Y., Dosovitskiy, A., Yosinski, J.
     (2016).
     > “[Plug & play generative networks: conditional iterative
     generation of
     > images in latent space]([64]https://arxiv.org/abs/1612.00005).
     [↩︎](
     > [65]https://openai.com/blog/dall-e/#rfref8)
     >
     > - Cho, J., Lu, J., Schwen, D., Hajishirzi, H., Kembhavi, A.
     (2020).
     > “[X-LXMERT: Paint, caption, and answer questions with multi-modal
     > transformers]([66]https://arxiv.org/abs/2009.11278)”. EMNLP 2020.
     [↩︎](
     > [67]https://openai.com/blog/dall-e/#rfref9)
     >
     > - Kingma, Diederik P., and Max Welling. “[Auto-encoding
     variational bayes](
     > [68]https://arxiv.org/abs/1312.6114).” arXiv preprint (2013).
     [↩︎](
     > [69]https://openai.com/blog/dall-e/#rfref10a) [↩︎](
     > [70]https://openai.com/blog/dall-e/#rfref10b)
     >
     > - Rezende, Danilo Jimenez, Shakir Mohamed, and Daan Wierstra.
     “[Stochastic
     > backpropagation and approximate inference in deep generative
     models](
     > [71]https://arxiv.org/abs/1401.4082).” arXiv preprint (2014).
     [↩︎](
     > [72]https://openai.com/blog/dall-e/#rfref11a) [↩︎](
     > [73]https://openai.com/blog/dall-e/#rfref11b)
     >
     > - Jang, E., Gu, S., Poole, B. (2016). “[Categorical
     reparametrization with
     > Gumbel-softmax]([74]https://arxiv.org/abs/1611.01144)”. [↩︎](
     > [75]https://openai.com/blog/dall-e/#rfref12a) [↩︎](
     > [76]https://openai.com/blog/dall-e/#rfref12b)
     >
     > - Maddison, C., Mnih, A., Teh, Y. W. (2016). “[The Concrete
     distribution:
     > a continuous relaxation of discrete random variables](
     > [77]https://arxiv.org/abs/1611.00712)”. [↩︎](
     > [78]https://openai.com/blog/dall-e/#rfref13a) [↩︎](
     > [79]https://openai.com/blog/dall-e/#rfref13b)
     >
     > - van den Oord, A., Vinyals, O., Kavukcuoglu, K. (2017). “[Neural
     discrete
     > representation learning]([80]https://arxiv.org/abs/1711.00937)”.
     [↩︎](
     > [81]https://openai.com/blog/dall-e/#rfref14a) [↩︎](
     > [82]https://openai.com/blog/dall-e/#rfref14b)
     >
     > - Razavi, A., van der Oord, A., Vinyals, O. (2019). “[Generating
     diverse
     > high-fidelity images with
     VQ-VAE-2]([83]https://arxiv.org/abs/1906.00446)”.
     > [↩︎]([84]https://openai.com/blog/dall-e/#rfref15a) [↩︎](
     > [85]https://openai.com/blog/dall-e/#rfref15b)
     >
     > - Andreas, J., Klein, D., Levine, S. (2017). “[Learning with
     Latent
     > Language]([86]https://arxiv.org/abs/1711.00482)”. [↩︎](
     > [87]https://openai.com/blog/dall-e/#rfref16)
     >
     > - Smolensky, P. (1990). “[Tensor product variable binding and the
     > representation of symbolic structures in connectionist systems](
     >
     [88]http://www.lscp.net/persons/dupoux/teaching/AT1_2014/papers/Smol
     ensky_1990_TensorProductVariableBinding.AI.pdf)”.
     > [↩︎]([89]https://openai.com/blog/dall-e/#rfref17a) [↩︎](
     > [90]https://openai.com/blog/dall-e/#rfref17b)
     >
     > - Plate, T. (1995). “[Holographic reduced representations:
     convolution
     > algebra for compositional distributed representations](
     > [91]https://www.ijcai.org/Proceedings/91-1/Papers/006.pdf)”. [↩︎](
     > [92]https://openai.com/blog/dall-e/#rfref18a) [↩︎](
     > [93]https://openai.com/blog/dall-e/#rfref18b)
     >
     > - Gayler, R. (1998). “[Multiplicative binding, representation
     operators &
     > analogy]([94]http://cogprints.org/502/)”. [↩︎](
     > [95]https://openai.com/blog/dall-e/#rfref19a) [↩︎](
     > [96]https://openai.com/blog/dall-e/#rfref19b)
     >
     > - Kanerva, P. (1997). “[Fully distributed representations](
     > [97]http://www.cap-lore.com/RWC97-kanerva.pdf)”. [↩︎](
     > [98]https://openai.com/blog/dall-e/#rfref20a) [↩︎](
     > [99]https://openai.com/blog/dall-e/#rfref20b)
     >
     > ---------------------------------------------------------------
     >
     > Authors
     > [Aditya
     Ramesh]([100]https://openai.com/blog/authors/aditya/)[Mikhail
     Pavlov](
     > [101]https://openai.com/blog/authors/mikhail/)[Gabriel Goh](
     > [102]https://openai.com/blog/authors/gabriel/)[Scott Gray](
     > [103]https://openai.com/blog/authors/scott/)
     > (Primary Authors)
     > [Mark Chen]([104]https://openai.com/blog/authors/mark/)[Rewon
     Child](
     > [105]https://openai.com/blog/authors/rewon/)[Vedant Misra](
     > [106]https://openai.com/blog/authors/vedant/)[Pamela Mishkin](
     > [107]https://openai.com/blog/authors/pamela/)[Gretchen Krueger](
     > [108]https://openai.com/blog/authors/gretchen/)[Sandhini Agarwal](
     > [109]https://openai.com/blog/authors/sandhini/)[Ilya Sutskever](
     > [110]https://openai.com/blog/authors/ilya/)
     > (Supporting Authors)
     > ---------------------------------------------------------------
     >
     > Filed Under
     > [Research](
     >
     [111]https://openai.com/blog/tags/research/)[Milestones](https://ope
     nai.com/blog/tags/milestones/)[Multimodal](https://openai.com/blog/t
     ags/multimodal/
     > )
     > ---------------------------------------------------------------
     >
     > Cover Artwork
     >
     > Justin Jay Wang
     >
     > ---------------------------------------------------------------
     >
     > Acknowledgments
     >
     > Thanks to the following for their feedback on this work and
     contributions
     > to this release: Alec Radford, Andrew Mayne, Jeff Clune, Ashley
     Pilipiszyn,
     > Steve Dowling, Jong Wook Kim, Lei Pan, Heewoo Jun, John Schulman,
     Michael
     > Tabatowski, Preetum Nakkiran, Jack Clark, Fraser Kelton, Jacob
     Jackson,
     > Greg Brockman, Wojciech Zaremba, Justin Mao-Jones, David Luan,
     Shantanu
     > Jain, Prafulla Dhariwal, Sam Altman, Pranav Shyam, Miles Brundage,
     Jakub
     > Pachocki, and Ryan Lowe.
     >
     > ---------------------------------------------------------------
     >
     > Contributions
     >
     > Aditya Ramesh was the project lead: he developed the approach,
     trained the
     > models, and wrote most of the blog copy.
     >
     > Aditya Ramesh, Mikhail Pavlov, and Scott Gray worked together to
     scale up
     > the model to 12 billion parameters, and designed the
     infrastructure used to
     > draw samples from the model.
     >
     > Aditya Ramesh, Gabriel Goh, and Justin Jay Wang worked together to
     create
     > the interactive visuals for the blog.
     >
     > Mark Chen and Aditya Ramesh created the images for Raven’s
     Progressives
     > Matrices.
     >
     > Rewon Child and Vedant Misra assisted in writing the blog.
     >
     > Pamela Mishkin, Gretchen Krueger, and Sandhini Agarwal advised on
     broader
     > impacts of the work and assisted in writing the blog.
     >
     > Ilya Sutskever oversaw the project and assisted in writing the
     blog.
     > -------------- next part --------------
     > A non-text attachment was scrubbed...
     > Name: not available
     > Type: text/html
     > Size: 45019 bytes
     > Desc: not available
     > URL: <
     >
     [112]https://lists.cpunks.org/pipermail/cypherpunks/attachments/2022
     0408/96a4e98c/attachment.txt
     > >
     >
     > ------------------------------
     >
     > Subject: Digest Footer
     >
     > _______________________________________________
     > cypherpunks mailing list
     > [113]cypherpunks@lists.cpunks.org
     > [114]https://lists.cpunks.org/mailman/listinfo/cypherpunks
     >
     >
     > ------------------------------
     >
     > End of cypherpunks Digest, Vol 106, Issue 93
     > ********************************************
     >
     -------------- next part --------------
     A non-text attachment was scrubbed...
     Name: not available
     Type: text/html
     Size: 39458 bytes
     Desc: not available
     URL:
     <[115]https://lists.cpunks.org/pipermail/cypherpunks/attachments/202
     20408/66867ca0/attachment.txt>
     ------------------------------
     Subject: Digest Footer
     _______________________________________________
     cypherpunks mailing list
     [116]cypherpunks@lists.cpunks.org
     [117]https://lists.cpunks.org/mailman/listinfo/cypherpunks
     ------------------------------
     End of cypherpunks Digest, Vol 106, Issue 94
     ********************************************

References

   1. mailto:cypherpunks-request@lists.cpunks.org
   2. mailto:cypherpunks@lists.cpunks.org
   3. https://lists.cpunks.org/mailman/listinfo/cypherpunks
   4. mailto:cypherpunks-request@lists.cpunks.org
   5. mailto:cypherpunks-owner@lists.cpunks.org
   6. mailto:g@xny.io
   7. mailto:cypherpunks@lists.cpunks.org
   8. mailto:TBMcrzLz46uyNHJXV9cg@mail.gmail.com
   9. mailto:cypherpunks-request@lists.cpunks.org
  10. mailto:cypherpunks@lists.cpunks.org
  11. https://lists.cpunks.org/mailman/listinfo/cypherpunks
  12. mailto:cypherpunks-request@lists.cpunks.org
  13. mailto:cypherpunks-owner@lists.cpunks.org
  14. mailto:coderman@protonmail.com
  15. mailto:coderman@protonmail.com
  16. mailto:cypherpunks@cpunks.org
  17. http://protonmail.com/
  18. https://openai.com/blog/dall-e/#fn1
  19. https://arxiv.org/abs/2005.14165
  20. https://openai.com/blog/image-gpt
  21. https://openai.com/blog/dall-e/#fn2
  22. https://openai.com/blog/dall-e/#rf14)[15](https://openai.com/blog/dall-e/#rf15
  23. https://openai.com/blog/dall-e/#rf10)[11](https://openai.com/blog/dall-e/#rf11
  24. https://openai.com/blog/dall-e/#rf12)[13](https://openai.com/blog/dall-e/#rf13
  25. https://openai.com/blog/clip/
  26. https://openai.com/blog/dall-e/#fn3
  27. https://openai.com/blog/dall-e/#summary
  28. https://openai.com/blog/dall-e/#fn4
  29. https://openai.com/blog/dall-e/#rf17)[18](https://openai.com/blog/dall-e/#rf18)[19](https://openai.com/blog/dall-e/#rf19)[20](https://openai.com/blog/dall-e/#rf20
  30. https://arxiv.org/abs/2102.12092
  31. https://openai.com/blog/dall-e/#rf1
  32. https://openai.com/blog/dall-e/#rf3
  33. https://openai.com/blog/dall-e/#rf4
  34. https://openai.com/blog/dall-e/#rf5
  35. https://openai.com/blog/dall-e/#rf2)[6](https://openai.com/blog/dall-e/#rf6)[7](https://openai.com/blog/dall-e/#rf7
  36. https://openai.com/blog/dall-e/#rf8
  37. https://openai.com/blog/dall-e/#rf9
  38. https://arxiv.org/abs/1906.00446
  39. https://openai.com/blog/clip/
  40. https://openai.com/blog/dall-e/#rf16
  41. https://openai.com/blog/dall-e/#fnref1
  42. https://openai.com/blog/dall-e/#rf14)[15](https://openai.com/blog/dall-e/#rf15
  43. https://openai.com/blog/dall-e/#rf10)[11](https://openai.com/blog/dall-e/#rf11
  44. https://openai.com/blog/dall-e/#rf12)[13](https://openai.com/blog/dall-e/#rf13
  45. https://openai.com/blog/dall-e/#fnref2
  46. https://openai.com/blog/dall-e/#summary
  47. https://openai.com/blog/dall-e/#fnref3
  48. https://openai.com/blog/dall-e/#rf17)[18](https://openai.com/blog/dall-e/#rf18)[19](https://openai.com/blog/dall-e/#rf19)[20](https://openai.com/blog/dall-e/#rf20
  49. https://openai.com/blog/dall-e/#fnref4
  50. https://arxiv.org/abs/1605.05396)
  51. https://openai.com/blog/dall-e/#rfref1
  52. https://arxiv.org/abs/1610.02454)
  53. https://openai.com/blog/dall-e/#rfref2
  54. https://arxiv.org/abs/1612.03242)
  55. https://openai.com/blog/dall-e/#rfref3
  56. https://arxiv.org/abs/1710.10916)
  57. https://openai.com/blog/dall-e/#rfref4
  58. https://arxiv.org/abs/1711.10485
  59. https://openai.com/blog/dall-e/#rfref5
  60. https://arxiv.org/abs/1902.10740)
  61. https://openai.com/blog/dall-e/#rfref6
  62. https://arxiv.org/abs/2011.03775)
  63. https://openai.com/blog/dall-e/#rfref7
  64. https://arxiv.org/abs/1612.00005
  65. https://openai.com/blog/dall-e/#rfref8
  66. https://arxiv.org/abs/2009.11278)
  67. https://openai.com/blog/dall-e/#rfref9
  68. https://arxiv.org/abs/1312.6114).
  69. https://openai.com/blog/dall-e/#rfref10a
  70. https://openai.com/blog/dall-e/#rfref10b
  71. https://arxiv.org/abs/1401.4082).
  72. https://openai.com/blog/dall-e/#rfref11a
  73. https://openai.com/blog/dall-e/#rfref11b
  74. https://arxiv.org/abs/1611.01144)
  75. https://openai.com/blog/dall-e/#rfref12a
  76. https://openai.com/blog/dall-e/#rfref12b
  77. https://arxiv.org/abs/1611.00712)
  78. https://openai.com/blog/dall-e/#rfref13a
  79. https://openai.com/blog/dall-e/#rfref13b
  80. https://arxiv.org/abs/1711.00937)
  81. https://openai.com/blog/dall-e/#rfref14a
  82. https://openai.com/blog/dall-e/#rfref14b
  83. https://arxiv.org/abs/1906.00446)
  84. https://openai.com/blog/dall-e/#rfref15a
  85. https://openai.com/blog/dall-e/#rfref15b
  86. https://arxiv.org/abs/1711.00482)
  87. https://openai.com/blog/dall-e/#rfref16
  88. http://www.lscp.net/persons/dupoux/teaching/AT1_2014/papers/Smolensky_1990_TensorProductVariableBinding.AI.pdf)
  89. https://openai.com/blog/dall-e/#rfref17a
  90. https://openai.com/blog/dall-e/#rfref17b
  91. https://www.ijcai.org/Proceedings/91-1/Papers/006.pdf)
  92. https://openai.com/blog/dall-e/#rfref18a
  93. https://openai.com/blog/dall-e/#rfref18b
  94. http://cogprints.org/502/)
  95. https://openai.com/blog/dall-e/#rfref19a
  96. https://openai.com/blog/dall-e/#rfref19b
  97. http://www.cap-lore.com/RWC97-kanerva.pdf)
  98. https://openai.com/blog/dall-e/#rfref20a
  99. https://openai.com/blog/dall-e/#rfref20b
 100. https://openai.com/blog/authors/aditya/)[Mikhail
 101. https://openai.com/blog/authors/mikhail/)[Gabriel
 102. https://openai.com/blog/authors/gabriel/)[Scott
 103. https://openai.com/blog/authors/scott/
 104. https://openai.com/blog/authors/mark/)[Rewon
 105. https://openai.com/blog/authors/rewon/)[Vedant
 106. https://openai.com/blog/authors/vedant/)[Pamela
 107. https://openai.com/blog/authors/pamela/)[Gretchen
 108. https://openai.com/blog/authors/gretchen/)[Sandhini
 109. https://openai.com/blog/authors/sandhini/)[Ilya
 110. https://openai.com/blog/authors/ilya/
 111. https://openai.com/blog/tags/research/)[Milestones](https://openai.com/blog/tags/milestones/)[Multimodal](https://openai.com/blog/tags/multimodal/
 112. https://lists.cpunks.org/pipermail/cypherpunks/attachments/20220408/96a4e98c/attachment.txt
 113. mailto:cypherpunks@lists.cpunks.org
 114. https://lists.cpunks.org/mailman/listinfo/cypherpunks
 115. https://lists.cpunks.org/pipermail/cypherpunks/attachments/20220408/66867ca0/attachment.txt
 116. mailto:cypherpunks@lists.cpunks.org
 117. https://lists.cpunks.org/mailman/listinfo/cypherpunks