Home › Topics › AI, Machine Learning & Data
Machine learning & deep learning: videos Hacker News recommends
Machine learning: neural networks, deep learning, backpropagation, training, optimization, reinforcement learning, AlphaGo, ML research lectures, Karpathy, Hinton, LeCun, Stanford CS231n. Below: every video in this topic that at least three HN users linked with real commentary, in at least three different months (39 talks, 24 explainers, 18 demos), best-scored first, with the comments on each video page.
- 17 HN recommenders 16 months 2022–2025HN treats it as the best starting point for really understanding backprop and neural nets, because Karpathy explains the why with intuition and builds everything in code.
- 16 HN recommenders 14 months 2017–2025HN treats it as the standard first stop for learning neural networks, praised for making the math intuitive.
- 10 HN recommenders 10 months 2020–2025G Google DeepMind · documentaryHN commenters call it a moving, well-made human story about AI and Go that works for non-technical viewers and does not date.
- 13 HN recommenders 10 months 2024–2026HN treats it as the go-to visual introduction to transformers, and many say it finally made attention and embeddings click.
- 10 HN recommenders 10 months 2018–2026HN considers it a classic, hilarious and sobering talk on ML inscrutability and tech hubris, often rewatched.
- 11 HN recommenders 11 months 2008–2020Recommended as the rigorous, math-heavy original course, deeper than the Coursera version, for learning machine learning.
- 10 HN recommenders 10 months 2015–2026The go-to accessible introduction to neuroevolution and NEAT, praised for crediting prior research.
- 10 HN recommenders 8 months 2025–2026HN's most frequent recommendation for a clear, approachable foundation in how LLMs work without heavy math.
- 9 HN recommenders 10 months 2015–2025Loved on HN as a hilarious, brilliant example of hacker-academic work and cited whenever game-playing AI or fuzzing comes up.
- 9 HN recommenders 9 months 2017–2026G Google DeepMind · courseFrequently recommended as an excellent, clear introductory RL course from the lead of AlphaGo, pairing well with Sutton and Barto.
- 14 HN recommenders 8 months 2023–2025It is the go-to recommendation for learning how transformers and LLMs actually work, praised for its clarity and Karpathy's teaching.
- 9 HN recommenders 7 months 2011–2013HN commenters recommended it for years as a simple, exciting overview of the deep learning wave.
- 8 HN recommenders 8 months 2023–2024Repeatedly named the best practical tutorial for using LLMs, with a well-liked fine-tuning section.
- 4 HN recommenders 6 months 2020–2022M Matroid · talkHN repeatedly points to it as the best public technical overview of Tesla's FSD approach, used both to defend and to critique Tesla's progress.
- 9 HN recommenders 6 months 2023–2026HN recommends it as the dense, approachable starting point for understanding LLMs and often cites it for specific claims about scaling and training.
- 6 HN recommenders 5 months 2020–2021Praised as a long but rewarding conversation, with commenters especially liking Bach's emphasis on modelling as a skill and his bridge between mind and computation.
- 6 HN recommenders 5 months 2017–2020Repeatedly called an excellent, practical introduction that covers a lot in two hours and explains issues academic textbooks skip.
- 7 HN recommenders 5 months 2012–2017Recommended as a simple, elegant explanation of dropout and its connection to how the brain works.
- 5 HN recommenders 6 months 2021–2025The go-to link in any anti-cheat thread for a concrete, well-delivered account of machine-learning cheat detection in production.
- 4 HN recommenders 5 months 2021–2024M Machine Learning Street Talk · interviewRecommended to people who find it inspiring or perspective-changing on pursuing goals, open-ended search and AI beyond optimization.
- 5 HN recommenders 5 months 2016–2023C caltech · courseRecommended repeatedly in 'where do I start with ML' threads as a clear, math-aware introduction.
- 7 HN recommenders 5 months 2022–2025Treated as the accessible reference on analog computing for neural nets, especially the Mythic AI segment.
- 5 HN recommenders 4 months 2021–2026Tom7 is an HN favorite, and this video is praised as hilarious, educational silly ML that keeps getting better.
- 5 HN recommenders 5 months 2024–2025Recommended as the best deep dive on tokenizers, worth the two hours for anyone working with LLMs.
- 6 HN recommenders 5 months 2016–2017HN commenters recommend it as an approachable first step into machine learning for programmers, with an apples-vs-oranges classifier.
- 5 HN recommenders 4 months 2024–2026HN treats it as the go-to visual explanation of attention, recommended to people who find text-based transformer explainers hard to follow.
- 5 HN recommenders 4 months 2018–2026M max4warn · talkHN points to it as the definitive example of server-side, behavioral, non-invasive anti-cheat using machine learning, often as a counterpoint to kernel-level anti-cheat.
- 4 HN recommenders 4 months 2020–2023S Seattle Applied Deep Learning · lectureRecommended as a clear explanation of why RNNs fall short and how transformers solve it.
- 6 HN recommenders 4 months 2020–2026Commenters recommend it as an entertaining, wide-ranging interview, and cite it for Hotz's views on end-to-end neural-net driving.
- 4 HN recommenders 4 months 2020–2025HN recommends it as an accessible, clear walkthrough of the transformer paper for people with some AI background.
- 3 HN recommenders 4 months 2018–2023Cited as the more accessible companion to the paper, and as the most interesting treatment of AD via compiling to categories.
- 4 HN recommenders 3 months 2017–2024Recommended as the most accessible introduction to backprop for people who struggle with the pure math.
- 3 HN recommenders 3 months 2019–2023Seen as the clearest introduction to the idea behind RLHF, and also borrowed by commenters as a metaphor for human motivation.
- 3 HN recommenders 3 months 2018–2025O ObservantVids · talkHN points to it as the sharpest, most-quoted critique of deep learning practice, and cites it whenever ML reliability or understanding is debated.
- 3 HN recommenders 4 months 2021–2025S sentdex · demoCited as an early, striking demo of neural networks acting as game engines and world models.
- 3 HN recommenders 3 months 2016–2026M MITCBMM · talkHN recommends it as a clear argument for why deep and cheap learning succeeds, often alongside the associated paper.
- 2 HN recommenders 3 months 2014–2016E Elizr · demoHN commenters use it as the canonical demo of deep reinforcement learning, noting that watching it teaches more than an article does.
- 4 HN recommenders 3 months 2017–2024HN recommends the series as a very accessible way to understand the math behind machine learning and LLMs.
- 3 HN recommenders 3 months 2025HN readers recommend it as an intuitive explanation of neural networks that shifts how people think about AI and language.
- 3 HN recommenders 3 months 2018–2021HN commenters point to it as a candid, contrarian view of self-driving approaches and the real limits of the business.
- 3 HN recommenders 3 months 2017–2018S Stanford University School of Engineering · lectureRecommended as one of the best free courses for learning modern deep learning for NLP.
- 3 HN recommenders 3 months 2019–2023Recommended as a fun, semi-technical intro to machine learning that holds kids' attention.
- 6 HN recommenders 3 months 2023–2025Recommended as the clearest overview of how LLM assistants are built and how to use them well.
- 3 HN recommenders 3 months 2015–2018HN commenters point beginners to this series as one of the clearest short walkthroughs of how neural networks and backpropagation work.
- 3 HN recommenders 3 months 2022–2025Cited for Karpathy's first-hand explanations of camera-only self-driving, transformers and ML trends.
- 3 HN recommenders 3 months 2024S Sasha Rush · lectureHN commenters recommend it for building intuition about state space models and the tradeoffs between transformer and SSM layers.
- 4 HN recommenders 3 months 2021–2023W WAD at CVPR · talkHN commenters cite it in Tesla threads as the primary-source explanation of why Tesla removed radar and how its vision depth estimation works.
- 3 HN recommenders 3 months 2007–2009G GoogleDeveloperDay · talkHN recommends it as the clear explanation of why Google's statistical, data-first approach works.
- 3 HN recommenders 3 months 2012–2026U UBC Computer Science · lectureRecommended as a favorite tech talk showing how huge data availability changes how problems are approached.
- 3 HN recommenders 3 months 2018–2024J Jakob Foerster · lectureRecommended as an enjoyable, clear introduction to information theory that pairs well with MacKay's free textbook.
- 3 HN recommenders 3 months 2009–2012R Robin Baumgarten · demoHN points to it as a vivid demo that plain A* search can beat fancier machine-learning approaches in game AI.
- 3 HN recommenders 3 months 2017–2018T The Research and Applied AI Summit - RAAIS · talkHN points to it as a technical talk from a chip designer on why AI hardware should put memory close to compute and use async data transfers.
- 3 HN recommenders 3 months 2023P Pascal Poupart · lectureHN recommends it to newcomers as a clear explanation of attention, including the query/key/value intuition.
- 2 HN recommenders 2 months 2024HN recommends it as a long but worthwhile way to demystify how language models work technically.
- 3 HN recommenders 3 months 2019–2024Cited both as a primary source on Tesla's technical autonomy approach and, later, for Musk's unmet robotaxi predictions.
- 5 HN recommenders 3 months 2017–2021Cited in floating-point threads as the main introduction to posits and unums as an alternative to IEEE floats.
- 3 HN recommenders 3 months 2016–2019J Joscha Bach · talkHN recommends it as an inspiring summary of a computational model of mind and a first lecture in a series on the brain as a computer.
- 3 HN recommenders 2 months 2023–2024G Graphics in 5 Minutes · explainerHN recommends it as a quick, non-dumbed-down way to get up to speed on how LLMs are built.
- 3 HN recommenders 3 months 2022–2025Pointed to as an accessible early explanation of transformers and attention for newcomers.
- 2 HN recommenders 2 months 2019–2021HN people send others here to hear Hawkins explain his theory in his own words, including reference frames and the old versus new brain.
- 2 HN recommenders 2 months 2022–2023HN considers the course one of the best hands-on ways into deep learning, praising the code-first teaching style.
- 3 HN recommenders 2 months 2018–2023Pointed to during self-driving news threads as an insider view of Waymo's progress, deep learning's role and its limits.
- 2 HN recommenders 2 months 2022–2026HN uses it as primary-source evidence on how Tesla's vision-based driving stack and training pipeline work.
- 2 HN recommenders 2 months 2025–2026HN points to it as an accessible explainer of AlphaFold and as an example of narrow, specialized ML delivering real scientific breakthroughs.
- 2 HN recommenders 2 months 2019–2025A agadmator's Chess Channel · explainerHN recommends it as a striking, well-explained example of AlphaZero's play and of zugzwang.
- 2 HN recommenders 2 months 2023–2025H hotchipsvideos · talkHN points to it for an insider view of why NVIDIA's AI gains came from design rather than process, and for data-movement power costs.
- 2 HN recommenders 2 months 2017–2019Recommended as a broad, practical view of AI's near-term impact from a leading practitioner, with his argument that worrying about evil AI is premature.
- 2 HN recommenders 2 months 2024–2025Recommended as a well-made, digestible introduction to scaling laws and why models cluster along a similar efficiency frontier.
- 2 HN recommenders 2 months 2014–2022M MediaArtTube · demoHN treats it as the classic reference for evolutionary simulation and genetic programming, an inspiration for many projects, with notes on evolution exploiting simulation bugs.
- 2 HN recommenders 2 months 2009–2014HN points to it as a source for Norvig's 'unreasonable effectiveness of data' argument and for his views on image search and the semantic web.
- 2 HN recommenders 2 months 2020–2021HN mentions it as a fun and slightly worrying example of AI systems behaving in unintended ways when optimizing.
- 2 HN recommenders 2 months 2021–2025I ISL and Collaborators · demoUsed as a go-to example of neural networks enhancing game rendering, referenced in later AI-graphics discussions.
- 2 HN recommenders 2 months 2024A Arts & Science - University of Toronto · interviewHN recommends it for Hinton's research history and the two pioneers reflecting on a decade of progress.
- 2 HN recommenders 2 months 2018–2026HN cites it as a fun, tangible way to teach machine learning, including to kids.
- 3 HN recommenders 2 months 2010–2026Cited as a watchable early introduction to deep learning from its pioneer, and remembered as a mind-blowing moment in the field.
- 2 HN recommenders 2 months 2018–2019Cited as an accessible explanation of AI denoising, which underpins real-time ray tracing on RTX hardware.
- 2 HN recommenders 2 months 2019–2021C CraftHub Events · talkHN cites it in algorithmic-bias threads for the impossibility result that an algorithm cannot be procedurally fair, group fair and maximally useful at once.
- 2 HN recommenders 2 months 2021Recommended in Elixir and machine learning threads as the introduction to what Nx makes possible.
- 2 HN recommenders 2 months 2023U UC Berkeley EECS · talkRecommended in LLM threads as an authoritative explanation from a ChatGPT architect of why models hallucinate and why imitation is not enough.
- 3 HN recommenders 2 months 2023–2024P Paul G. Allen School · lectureHN commenters cite it for NVIDIA's perspective on AI hardware efficiency, including logarithmic number formats and energy use.
- 3 HN recommenders 2 months 2023C CBS Mornings · interviewRecommended as a more nuanced look at Hinton's views than headlines, especially his argument that LLMs are more than auto-complete.
- 2 HN recommenders 2 months 2025–2026A Alex Kantrowitz · podcast episodePointed to as LeCun's argument for the limits of LLMs and the need for world models.
- 2 HN recommenders 2 months 2017–2018T trwappers · lectureRecommended as Hinton's own explanation of capsule networks and his critique of pooling in CNNs.
- 3 HN recommenders 2 months 2017–2024Recommended as an accessible, visual way to understand backpropagation and neural networks.
- 2 HN recommenders 2 months 2018–2025S Stanford University School of Engineering · lectureHN recommends the CS231n lectures as a solid, applied deep learning course for self-study.
- 2 HN recommenders 2 months 2019–2025HN commenters point to it as an interesting conversation with the creator of Swift and LLVM, especially for compilers and ML compilation.
- 2 HN recommenders 2 months 2016–2021B bilkable · documentaryRecommended as a historical look at the AI winter debate and a demolition of the expert systems hype.
- 1 HN recommenders 1 months 2024–2025Y Yosh · explainerRecommended as an approachable explanation of how reinforcement learning works in practice, and cited for the constraints needed to stop exploits.
- 1 HN recommenders 1 months 2023–2026HN people point to it as a clear, skeptical take on AI hype and the risks of unreliable AI classification, such as in mushroom foraging books.
- 2 HN recommenders 1 months 2016–2023HN lists it as a free, brilliant introduction to deep learning and computer vision, often within ML self-study plans.
- 1 HN recommenders 1 months 2011–2023Z Zdenek Kalal · demoHN found it a nifty demo and cites it as a primitive but effective learning tracker that predates modern deep-learning trackers.
- 1 HN recommenders 1 months 2013–2017Recommended as Hawkins' own accessible statement of his brain-inspired theory of intelligence and its software implementation.
- 1 HN recommenders 1 months 2021–2022G GothamChess · commentaryHN points to it as an entertaining analysis of AlphaZero's play in threads about chess engines.
- 1 HN recommenders 1 months 2020M Matroid · talkCited in hardware threads as a Keller talk on the different ways of doing parallel processing.
- 1 HN recommenders 1 months 2023–2024Cited as a fun, unconventional example of neural networks built from floating point error.
- 1 HN recommenders 1 months 2016–2025J Jason Yosinski · demoHN points to it as an intuitive way to see what hidden layers of a convnet learn, and as a reference for hierarchical feature learning.
- 1 HN recommenders 1 months 2013–2024HN cites it as an early impressive real-time speech translation demo, often in discussions of voice-preserving translation and later AI demos.
- 1 HN recommenders 1 months 2013–2019HN people point to it as the canonical explanation from the method's author whenever t-SNE comes up.
- 1 HN recommenders 1 months 2016–2017R Roger Luedecke · demoCited as a vivid example of what Deep Dream and feature visualization look like, resembling psychedelic visuals.
- 1 HN recommenders 1 months 2019–20233 3kliksphilip · explainerHN cites it as a source for how Valve uses machine learning on player behavior to detect cheating.
Showing the 100 best-scored of 128. Use search to find the rest.
Questions
What is the most recommended machine learning & deep learning video on Hacker News?
The spelled-out intro to neural networks and backpropagation: building micrograd by Andrej Karpathy: HN treats it as the best starting point for really understanding backprop and neural nets, because Karpathy explains the why with intuition and builds everything in code.
How is this machine learning & deep learning list ranked?
By HackerTube's score: the number of distinct months in which an HN comment recommended the video, plus half a point for every month with a strong recommendation. One viral thread counts less than steady recommendations over years.
Where do the videos come from?
From every Hacker News comment between 2007 and 2026 that linked a YouTube video, labeled by an AI model as a recommendation, a citation, a joke or a criticism. The list is published by HackerTube under ODC-By 1.0; this edition adds indexable pages and the comment context.
Video list and Hacker News comment labels from HackerTube (prompted by @karpathy), released under ODC-By 1.0, built on the open-index/hacker-news archive. Hacker News data is provided by Y Combinator; comments remain the work of their authors. Video titles, channel names and thumbnails belong to their creators and are shown via YouTube. HackerTube Watch is an unofficial edition. Data export of 2026-10-31.