Yannic Kilcher Videos (Audio Only)

 #parti #ai #aiart  Parti is a new autoregressive text-to-image model that shows just how much scale can achieve. This model's outputs are crips, accurate, realistic, and can combine arbitrary styles, concepts, and fulfil even challenging requests. OUTLINE: 0:00 - Introduction 2:40 - Example Outputs 6:00 - Model Architecture 17:15 - Datasets (incl. PartiPrompts) 21:45 - Experimental Results 27:00 - Picking a cherry tree 29:30 - Failure cases 33:20 - Final comments Website: https://parti.research.google/ Paper: https://arxiv.org/abs/2206.10789 Github: https://github.com/google-research/parti Links: Homepage: https://ykilcher.com Merch: https://ykilcher.com/merch YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ykilcher.com/discord LinkedIn: https://www.linkedin.com/in/ykilcher If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://www.subscribestar.com/yannick... Patreon: https://www.patreon.com/yannickilcher Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

#lamda #google #ai  Google engineer Blake Lemoine was put on leave after releasing proprietary information: An interview with the chatbot LaMDA that he believes demonstrates that this AI is, in fact, sentient. We analyze the claims and the interview in detail and trace how a statistical machine managed to convince at least one human that it is more than just an algorithm. OUTLINE: 0:00 - Whistleblower put on leave 4:30 - What is a language model? 6:40 - The prompt is the key 10:40 - Who are we talking to exactly? 12:50 - LaMDA analyzes stories 15:20 - Fear, pain, and consent 20:25 - How would we recognize sentience? When is a machine conscious? References: https://cajundiscordian.medium.com/is-lamda-sentient-an-interview-ea64d916d917 https://cajundiscordian.medium.com/what-is-lamda-and-what-does-it-want-688632134489 https://www.washingtonpost.com/technology/2022/06/11/google-ai-lamda-blake-lemoine/ https://www.theguardian.com/technology/2022/jun/12/google-engineer-ai-bot-sentient-blake-lemoine https://www.businessinsider.com/transcript-of-sentient-google-ai-chatbot-was-edited-for-readability-2022-6?inline-endstory-related-recommendations=&r=US&IR=T Links: Homepage: https://ykilcher.com Merch: https://ykilcher.com/merch YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ykilcher.com/discord BitChute: https://www.bitchute.com/channel/yannic-kilcher LinkedIn: https://www.linkedin.com/in/ykilcher If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://www.subscribestar.com/yannickilcher Patreon: https://www.patreon.com/yannickilcher Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

Your updates directly from the state of the art in Machine Learning! OUTLINE: 0:00 - Intro 0:30 - DeepMind's Flamingo: Unified Vision-Language Model 8:25 - LiT: Locked Image Tuning 10:20 - Jurassic X & MRKL Systems 15:05 - Helpful Things 22:40 - This AI does not exist References: DeepMind's Flamingo: Unified Vision-Language Model https://www.deepmind.com/blog/tacklin... https://storage.googleapis.com/deepmi... https://twitter.com/Inoryy/status/152... LiT: Locked Image Tuning https://ai.googleblog.com/2022/04/loc... https://google-research.github.io/vis... Jurassic X & MRKL Systems https://www.ai21.com/blog/jurassic-x-... https://arxiv.org/pdf/2205.00445.pdf https://arxiv.org/pdf/2204.10019.pdf https://studio.ai21.com/jurassic-x StyleGAN Human https://stylegan-human.github.io/ https://github.com/stylegan-human/Sty... https://huggingface.co/spaces/hysts/S... Helpful Things https://github.com/rish-16/grafog https://huggingface.co/bertin-project... https://github.com/pytorch/torchdistx https://pytorch.org/torchdistx/latest... https://github.com/Netflix/vectorflow... https://iclr-blog-track.github.io/202... https://twitter.com/DeepMind/status/1... https://github.com/ai-forever/mgpt https://github.com/cleanlab/cleanlab https://efficientdlbook.com/?utm_sour... https://minihack-editor.github.io/ https://mugen-org.github.io/ https://www.amazon.science/blog/amazo... https://github.com/phuselab/openFACS?... https://medium.com/pytorch/avalanche-... This AI does not exist https://thisaidoesnotexist.com/ Links: Merch: https://ykilcher.com/merch TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://discord.gg/4H8xxDF BitChute: https://www.bitchute.com/channel/yann... LinkedIn: https://www.linkedin.com/in/ykilcher BiliBili: https://space.bilibili.com/2017636191 If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://www.subscribestar.com/yannick... Patreon: https://www.patreon.com/yannickilcher Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

#mlnews #dalle #gpt3 An inside look of what's happening in the ML world! Sponsor: Weights & Biases https://wandb.me/yannic OUTLINE: 0:00 - Intro 0:20 - Sponsor: Weights & Biases 1:40 - Meta AI releases OPT-175B 4:55 - CoCa: New CLIP-Competitor 8:15 - DALL-E Mega is training 10:05 - TorToiSe TTS is amazing! 11:50 - Investigating Vision Transformers 12:50 - Hugging Face Deep RL class launched 13:40 - Helpful Things 17:00 - John Deere's driverless tractors References: Meta AI releases OPT-175B https://ai.facebook.com/blog/democratizing-access-to-large-scale-language-models-with-opt-175b/ https://arxiv.org/abs/2205.01068 https://arxiv.org/pdf/2205.01068.pdf https://github.com/facebookresearch/metaseq/tree/main/projects/OPT https://github.com/facebookresearch/metaseq/blob/main/projects/OPT/chronicles/OPT175B_Logbook.pdf https://github.com/facebookresearch/metaseq/tree/main/projects/OPT/chronicles https://twitter.com/yoavgo/status/1522150063815987201 CoCa: New CLIP-Competitor https://arxiv.org/abs/2205.01917 https://arxiv.org/pdf/2205.01917.pdf DALL-E Mega is training https://twitter.com/borisdayma https://twitter.com/borisdayma/status/1521891895001112577 https://wandb.ai/dalle-mini/dalle-mini/reports/DALL-E-Mega--VmlldzoxODMxMDI2 TorToiSe TTS is amazing! https://github.com/neonbjb/tortoise-tts https://nonint.com/static/tortoise_v2_examples.html https://colab.research.google.com/drive/1wVVqUPqwiDBUVeWWOUNglpGhU3hg_cbR https://github.com/neonbjb Investigating Vision Transformers https://github.com/sayakpaul/probing-vits/?utm_source=pocket_mylist https://twitter.com/RisingSayak/status/1515918406171914240?utm_source=pocket_mylist https://keras.io/examples/vision/probing_vits/ https://github.com/sayakpaul/probing-vits/tree/main/notebooks?utm_source=pocket_mylist Hugging Face Deep RL class launched https://github.com/huggingface/deep-rl-class Helpful Things https://merantix-momentum.com/technology/squirrel/?utm_source=pocket_mylist https://github.com/merantix-momentum/squirrel-core?utm_source=pocket_mylist https://pyscript.net/?utm_source=pocket_mylist https://github.com/google-research/big_vision https://deepsportradar.github.io/challenge.html https://github.com/DeepSportRadar/camera-calibration-challenge https://twitter.com/alekseykorshuk/status/1515989357961920514?utm_source=pocket_mylist https://github.com/AlekseyKorshuk/huggingnft John Deere's driverless tractors https://thenextweb.com/news/john-deere-slowly-becoming-one-worlds-most-important-ai-companies https://tractorhacking.github.io/ Links: Merch: https://ykilcher.com/merch TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://discord.gg/4H8xxDF BitChute: https://www.bitchute.com/channel/yannic-kilcher LinkedIn: https://www.linkedin.com/in/ykilcher BiliBili: https://space.bilibili.com/2017636191 If you want to support me, the best thing to do is to share out the content :)

#nft #gan #ai Today we build our own AI that can create as many bored apes as we want! Fungibility for everyone! Try the model here: https://huggingface.co/spaces/ykilcher/apes or here: https://ykilcher.com/apes Files & Models here: https://huggingface.co/ykilcher/apes/tree/main Code here: https://github.com/yk/apes-public (for the "what's your ape" app, look for the file interface_projector.py) This video is sponsored by BrightData, use this link for free credits: https://brightdata.grsm.io/yannickilcher OUTLINE: 0:00 - Introduction 2:05 - Generative Adversarial Networks 3:40 - Scraping Opensea with BrightData 7:55 - Training the GAN 11:35 - Here are the results! 15:20 - Diving deeper into BrightData References: Stylegan 3 imagery: https://nvlabs.github.io/stylegan3/ Bored Ape Yacht Club NFT Collection: https://opensea.io/collection/boredapeyachtclub Better GANFT model: https://medium.com/@nathancooperjones/these-bored-apes-do-not-exist-6bed2c73f02c Abstract AI-created apes: https://opensea.io/collection/gan-apes-nft https://mobile.twitter.com/gannft Another good model: https://twitter.com/cyrilzakka/status/1463944040878071811 StyleGAN2 versions: https://thispersondoesnotexist.com/ https://thissneakerdoesnotexist.com/ https://thischairdoesnotexist.com/ GANs: https://en.wikipedia.org/wiki/Generative_adversarial_network https://arxiv.org/pdf/1406.2661.pdf StyleGAN3: https://nvlabs.github.io/stylegan3/ StyleGAN2 code: https://github.com/NVlabs/stylegan2-ada-pytorch CLIP: https://openai.com/blog/clip/ DALL-E 2 images: https://twitter.com/search?q=%23dalle&f=image My music video: https://www.youtube.com/watch?v=2iq7WXSw26s BrightData Links: https://brightdata.com/products/data-collector https://brightdata.com/testimonials https://brightdata.com/use-cases/adtech https://brightdata.com/use-cases/social-media-for-marketing https://brightdata.com/use-cases/ecommerce Links: Merch: https://ykilcher.com/merch TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://discord.gg/4H8xxDF BitChute: https://www.bitchute.com/channel/yannic-kilcher LinkedIn: https://www.linkedin.com/in/ykilcher BiliBili: https://space.bilibili.com/2017636191 If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this), find options at https://ykilcher.com

#saycan #robots #ai This is an interview with the authors Brian Ichter, Karol Hausman, and Fei Xia. Original Paper Review Video: https://youtu.be/Ru23eWAQ6_E Large Language Models are excellent at generating plausible plans in response to real-world problems, but without interacting with the environment, they have no abilities to estimate which of these plans are feasible or appropriate. SayCan combines the semantic capabilities of language models with a bank of low-level skills, which are available to the agent as individual policies to execute. SayCan automatically finds the best policy to execute by considering a trade-off between the policy's ability to progress towards the goal, given by the language model, and the policy's probability of executing successfully, given by the respective value function. The result is a system that can generate and execute long-horizon action sequences in the real world to fulfil complex tasks. OUTLINE: 0:00 - Introduction & Setup 3:40 - Acquiring atomic low-level skills 7:45 - How does the language model come in? 11:45 - Why are you scoring instead of generating? 15:20 - How do you deal with ambiguity in language? 20:00 - The whole system is modular 22:15 - Going over the full algorithm 23:20 - What if an action fails? 24:30 - Debunking a marketing video :) 27:25 - Experimental Results 32:50 - The insane scale of data collection 40:15 - How do you go about large-scale projects? 43:20 - Where did things go wrong? 45:15 - Where do we go from here? 52:00 - What is the largest unsolved problem in this? 53:35 - Thoughts on the Tesla Bot 55:00 - Final thoughts Paper: https://arxiv.org/abs/2204.01691 Website: https://say-can.github.io/ Abstract: Large language models can encode a wealth of semantic knowledge about the world. Such knowledge could be extremely useful to robots aiming to act upon high-level, temporally extended instructions expressed in natural language. However, a significant weakness of language models is that they lack real-world experience, which makes it difficult to leverage them for decision making within a given embodiment. For example, asking a language model to describe how to clean a spill might result in a reasonable narrative, but it may not be applicable to a particular agent, such as a robot, that needs to perform this task in a particular environment. We propose to provide real-world grounding by means of pretrained skills, which are used to constrain the model to propose natural language actions that are both feasible and contextually appropriate. The robot can act as the language model's "hands and eyes," while the language model supplies high-level semantic knowledge about the task. We show how low-level skills can be combined with large language models so that the language model provides high-level knowledge about the procedures for performing complex and temporally-extended instructions, while value functions associated with these skills provide the grounding necessary to connect this knowledge to a particular physical environment. Authors: Michael Ahn, Anthony Brohan, Noah Brown, Yevgen Chebotar, Omar Cortes, Byron David, Chelsea Finn, Keerthana Gopalakrishnan, Karol Hausman, Alex Herzog, Daniel Ho, Jasmine Hsu, Julian Ibarz, Brian Ichter, Alex Irpan, Eric Jang, Rosario Jauregui Ruano, Kyle Jeffrey, Sally Jesmonth, Nikhil J Joshi, Ryan Julian, Dmitry Kalashnikov, Yuheng Kuang, Kuang-Huei Lee, Sergey Levine, Yao Lu, Linda Luu, Carolina Parada, Peter Pastor, Jornell Quiambao, Kanishka Rao, Jarek Rettinghouse, Diego Reyes, Pierre Sermanet, Nicolas Sievers, Clayton Tan, Alexander Toshev, Vincent Vanhoucke, Fei Xia, Ted Xiao, Peng Xu, Sichun Xu, Mengyuan Yan

#saycan #robots #ai Large Language Models are excellent at generating plausible plans in response to real-world problems, but without interacting with the environment, they have no abilities to estimate which of these plans are feasible or appropriate. SayCan combines the semantic capabilities of language models with a bank of low-level skills, which are available to the agent as individual policies to execute. SayCan automatically finds the best policy to execute by considering a trade-off between the policy's ability to progress towards the goal, given by the language model, and the policy's probability of executing successfully, given by the respective value function. The result is a system that can generate and execute long-horizon action sequences in the real world to fulfil complex tasks. Sponsor: Zeta Alpha https://zeta-alpha.com Use code YANNIC for 20% off! OUTLINE: 0:00 - Introduction & Overview 3:20 - Sponsor: Zeta Alpha 5:00 - Using language models for action planning 8:00 - Combining LLMs with learned atomic skills 16:50 - The full SayCan system 20:30 - Experimental setup and data collection 21:25 - Some weaknesses & strengths of the system 27:00 - Experimental results Paper: https://arxiv.org/abs/2204.01691 Website: https://say-can.github.io/ Abstract: Large language models can encode a wealth of semantic knowledge about the world. Such knowledge could be extremely useful to robots aiming to act upon high-level, temporally extended instructions expressed in natural language. However, a significant weakness of language models is that they lack real-world experience, which makes it difficult to leverage them for decision making within a given embodiment. For example, asking a language model to describe how to clean a spill might result in a reasonable narrative, but it may not be applicable to a particular agent, such as a robot, that needs to perform this task in a particular environment. We propose to provide real-world grounding by means of pretrained skills, which are used to constrain the model to propose natural language actions that are both feasible and contextually appropriate. The robot can act as the language model's "hands and eyes," while the language model supplies high-level semantic knowledge about the task. We show how low-level skills can be combined with large language models so that the language model provides high-level knowledge about the procedures for performing complex and temporally-extended instructions, while value functions associated with these skills provide the grounding necessary to connect this knowledge to a particular physical environment. We evaluate our method on a number of real-world robotic tasks, where we show the need for real-world grounding and that this approach is capable of completing long-horizon, abstract, natural language instructions on a mobile manipulator. The project's website and the video can be found at this https URL Authors: Michael Ahn, Anthony Brohan, Noah Brown, Yevgen Chebotar, Omar Cortes, Byron David, Chelsea Finn, Keerthana Gopalakrishnan, Karol Hausman, Alex Herzog, Daniel Ho, Jasmine Hsu, Julian Ibarz, Brian Ichter, Alex Irpan, Eric Jang, Rosario Jauregui Ruano, Kyle Jeffrey, Sally Jesmonth, Nikhil J Joshi, Ryan Julian, Dmitry Kalashnikov, Yuheng Kuang, Kuang-Huei Lee, Sergey Levine, Yao Lu, Linda Luu, Carolina Parada, Peter Pastor, Jornell Quiambao, Kanishka Rao, Jarek Rettinghouse, Diego Reyes, Pierre Sermanet, Nicolas Sievers, Clayton Tan, Alexander Toshev, Vincent Vanhoucke, Fei Xia, Ted Xiao, Peng Xu, Sichun Xu, Mengyuan Yan

#ai #accel #evolution This is an interview with the authors Jack Parker-Holder and Minqi Jiang. Original Paper Review Video: https://www.youtube.com/watch?v=povBD... Automatic curriculum generation is one of the most promising avenues for Reinforcement Learning today. Multiple approaches have been proposed, each with their own set of advantages and drawbacks. This paper presents ACCEL, which takes the next step into the direction of constructing curricula for multi-capable agents. ACCEL combines the adversarial adaptiveness of regret-based sampling methods with the capabilities of level-editing, usually found in Evolutionary Methods. OUTLINE: 0:00 - Intro 1:00 - Start of interview 4:45 - How did you get into this field? 8:10 - What is minimax regret? 11:45 - What levels does the regret objective select? 14:20 - Positive value loss (correcting my mistakes) 21:05 - Why is the teacher not learned? 24:45 - How much domain-specific knowledge is needed? 29:30 - What problems is this applicable to? 33:15 - Single agent vs population of agents 37:25 - Measuring and balancing level difficulty 40:35 - How does generalization emerge? 42:50 - Diving deeper into the experimental results 47:00 - What are the unsolved challenges in the field? 50:00 - Where do we go from here? Website: https://accelagent.github.io Paper: https://arxiv.org/abs/2203.01302 ICLR Workshop: https://sites.google.com/view/aloe2022 Book on topic: https://www.oreilly.com/radar/open-en... Abstract: It remains a significant challenge to train generally capable agents with reinforcement learning (RL). A promising avenue for improving the robustness of RL agents is through the use of curricula. One such class of methods frames environment design as a game between a student and a teacher, using regret-based objectives to produce environment instantiations (or levels) at the frontier of the student agent's capabilities. These methods benefit from their generality, with theoretical guarantees at equilibrium, yet they often struggle to find effective levels in challenging design spaces. By contrast, evolutionary approaches seek to incrementally alter environment complexity, resulting in potentially open-ended learning, but often rely on domain-specific heuristics and vast amounts of computational resources. In this paper we propose to harness the power of evolution in a principled, regret-based curriculum. Our approach, which we call Adversarially Compounding Complexity by Editing Levels (ACCEL), seeks to constantly produce levels at the frontier of an agent's capabilities, resulting in curricula that start simple but become increasingly complex. ACCEL maintains the theoretical benefits of prior regret-based methods, while providing significant empirical gains in a diverse set of environments. An interactive version of the paper is available at this http URL. Authors: Jack Parker-Holder, Minqi Jiang, Michael Dennis, Mikayel Samvelyan, Jakob Foerster, Edward Grefenstette, Tim Rocktäschel Links: TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://discord.gg/4H8xxDF BitChute: https://www.bitchute.com/channel/yann... LinkedIn: https://www.linkedin.com/in/ykilcher BiliBili: https://space.bilibili.com/2017636191 If you want to support me, the best thing to do is to share out the content :)

#ai #accel #evolution Automatic curriculum generation is one of the most promising avenues for Reinforcement Learning today. Multiple approaches have been proposed, each with their own set of advantages and drawbacks. This paper presents ACCEL, which takes the next step into the direction of constructing curricula for multi-capable agents. ACCEL combines the adversarial adaptiveness of regret-based sampling methods with the capabilities of level-editing, usually found in Evolutionary Methods. OUTLINE: 0:00 - Intro & Demonstration 3:50 - Paper overview 5:20 - The ACCEL algorithm 15:25 - Looking at the pseudocode 23:10 - Approximating regret 33:45 - Experimental results 40:00 - Discussion & Comments Website: https://accelagent.github.io Paper: https://arxiv.org/abs/2203.01302 Abstract: It remains a significant challenge to train generally capable agents with reinforcement learning (RL). A promising avenue for improving the robustness of RL agents is through the use of curricula. One such class of methods frames environment design as a game between a student and a teacher, using regret-based objectives to produce environment instantiations (or levels) at the frontier of the student agent's capabilities. These methods benefit from their generality, with theoretical guarantees at equilibrium, yet they often struggle to find effective levels in challenging design spaces. By contrast, evolutionary approaches seek to incrementally alter environment complexity, resulting in potentially open-ended learning, but often rely on domain-specific heuristics and vast amounts of computational resources. In this paper we propose to harness the power of evolution in a principled, regret-based curriculum. Our approach, which we call Adversarially Compounding Complexity by Editing Levels (ACCEL), seeks to constantly produce levels at the frontier of an agent's capabilities, resulting in curricula that start simple but become increasingly complex. ACCEL maintains the theoretical benefits of prior regret-based methods, while providing significant empirical gains in a diverse set of environments. An interactive version of the paper is available at this http URL. Authors: Jack Parker-Holder, Minqi Jiang, Michael Dennis, Mikayel Samvelyan, Jakob Foerster, Edward Grefenstette, Tim Rocktäschel Links: TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://discord.gg/4H8xxDF BitChute: https://www.bitchute.com/channel/yann... LinkedIn: https://www.linkedin.com/in/ykilcher BiliBili: https://space.bilibili.com/2017636191 If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://www.subscribestar.com/yannick... Patreon: https://www.patreon.com/yannickilcher Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

#laion #clip #dalle LAION-5B is an open, free dataset consisting of over 5 billion image-text-pairs. Today's video is an interview with three of its creators. We dive into the mechanics and challenges of operating at such large scale, how to keep cost low, what new possibilities are enabled with open datasets like this, and how to best handle safety and legal concerns. OUTLINE: 0:00 - Intro 1:30 - Start of Interview 2:30 - What is LAION? 11:10 - What are the effects of CLIP filtering? 16:40 - How big is this dataset? 19:05 - Does the text always come from the alt-property? 22:45 - What does it take to work at scale? 25:50 -When will we replicate DALL-E? 31:30 - The surprisingly efficient pipeline 35:20 - How do you cover the S3 costs? 40:30 - Addressing safety & legal concerns 55:15 - Where can people get started? References: LAION website: https://laion.ai/ LAION Discord: https://discord.com/invite/mVcgxMPD7e LAION-5B: https://laion.ai/laion-5b-a-new-era-o... img2dataset tool: https://github.com/rom1504/img2dataset LAION-400M: https://paperswithcode.com/dataset/la... Links: TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://discord.gg/4H8xxDF BitChute: https://www.bitchute.com/channel/yann... LinkedIn: https://www.linkedin.com/in/ykilcher BiliBili: https://space.bilibili.com/2017636191 If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://www.subscribestar.com/yannick... Patreon: https://www.patreon.com/yannickilcher Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n