Home › Topics › AI, Machine Learning & Data
Computer vision, speech & NLP: videos Hacker News recommends
Perception and language AI: image recognition, object detection, OCR, speech recognition, text-to-speech, machine translation, natural language processing, face recognition, classical AI and expert systems. Below: every video in this topic that at least three HN users linked with real commentary, in at least three different months (33 demos, 19 talks, 11 comedy videos), best-scored first, with the comments on each video page.
- 9 HN recommenders 7 months 2011–2013HN commenters recommended it for years as a simple, exciting overview of the deep learning wave.
- 5 HN recommenders 6 months 2020–2023It is the go-to recommendation whenever someone asks about voice coding or RSI-friendly programming setups.
- 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.
- 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.
- 6 HN recommenders 6 months 2015–2026HN recommends it as an easy, clear intro to the DCT that finally made it click for several commenters.
- 5 HN recommenders 5 months 2021–2025Recommended as one of the best explanations of Fourier transforms and a clear demo of analog optical computing.
- 5 HN recommenders 5 months 2024–2025Recommended as the best deep dive on tokenizers, worth the two hours for anyone working with LLMs.
- 4 HN recommenders 4 months 2012–2022HN commenters recommend it as the clearest account of human computation and games with a purpose, straight from the inventor.
- 4 HN recommenders 4 months 2017–2025HN commenters recommend it as a fun, short talk that shows how HDR photography actually works through an absurdly playful implementation.
- 2 HN recommenders 4 months 2016–2025Regarded as the seminal talk on Dasher, recommended in threads on accessible and alternative text input.
- 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.
- 4 HN recommenders 4 months 2013–2026M mm648230 · demoCited whenever threads discuss recovering hidden images or non-line-of-sight imaging, as a clear demonstration of light transport.
- 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.
- 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 2024–2026HN recommends it as an accessible introduction to Gaussian splats, made by people who understand the subject.
- 4 HN recommenders 3 months 2022–2026Recommended in address and OCR threads as a look at the last human mail-coding operation.
- 3 HN recommenders 3 months 2010–2023T TheMcphearson · demoHN recommends it as the canonical talking-piano example, uncanny and impressive once you read the captions.
- 3 HN recommenders 3 months 2022–2025Pointed to as an accessible early explanation of transformers and attention for newcomers.
- 2 HN recommenders 2 months 2021–2024S ShortCircuit · demoCited as a demo of GPU-powered noise suppression that works remarkably well, in threads on mic muting and speech enhancement.
- 2 HN recommenders 2 months 2018–2024I Ishikawa Group Laboratory · demoHN commenters bring it up in book-scanning threads as an impressive non-destructive method that is not commercially available.
- 2 HN recommenders 2 months 2018–2022Recommended as informal, long-form live coding to watch, though some commenters criticize his style.
- 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.
- 2 HN recommenders 2 months 2020–2023HN commenters share it as a favorite example of upscaled vintage footage that makes the early 1900s feel present, though some find the colorization off.
- 2 HN recommenders 2 months 2015–2019H Hound by SoundHound Inc. · demoHN viewers were impressed by its speed and saw it as a glimpse of the future of voice search; later it appears in hiring posts.
- 2 HN recommenders 2 months 2013–2024D Daniel CohenOr · demoHN recalls it as a mind-blowing pre-AI demo of 2D-to-3D object extraction.
- 3 HN recommenders 2 months 2014–2023HN loves it as a funny, inspiring hobby project and calls it one of the best conference talks ever.
- 2 HN recommenders 2 months 2012–2016HN recommends it as a technical talk aimed at a real engineering audience, with live demos of perception and pre-mapped roads.
- 3 HN recommenders 2 months 2021–2023Pointed to as the long-form interview for understanding Lenat's work, especially after his death.
- 2 HN recommenders 2 months 2016–2024A Adobe Creative Cloud · demoHN cites it as the early example of voice cloning and audio deepfakes, with some recommending Peele's reaction and others calling the demo fake or never shipped.
- 2 HN recommenders 2 months 2023–2026HN recommends it as the best overview of Cursorless, likened to vim with your voice, and relevant to accessibility and voice coding discussions.
- 2 HN recommenders 2 months 2023HN points to it as the accessible explanation of why glitch tokens exist whenever tokenizers or odd GPT behavior come up.
- 2 HN recommenders 2 months 2011–2012HN people recommend it as a look at how to get people to eagerly do useful collective work, and as the origin of Duolingo.
- 3 HN recommenders 2 months 2021–2023S synesthesiam · demoHN points to it as proof that offline TTS can sound natural, relevant to private voice assistant alternatives.
- 2 HN recommenders 2 months 2020–2024HN points to it as an impressive example of ML-based video restoration, and as the test case in the debate over whether upscaling historical footage is respectful or misleading.
- 2 HN recommenders 2 months 2017–2018T trwappers · lectureRecommended as Hinton's own explanation of capsule networks and his critique of pooling in CNNs.
- 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.
- 1 HN recommenders 1 months 2016M Mobileye · talkRecommended as an accessible technical explanation of Mobileye's approach, and also cited in disputes over Tesla Autopilot.
- 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 2015–2018V VideoFunStation · comedy videoPosted as the obligatory joke in any thread about speech recognition, and recommended in a thread on what makes people laugh.
- 1 HN recommenders 1 months 2013–2019Recommended as a great technical talk from the pioneer of human computation.
- 1 HN recommenders 1 months 2020–2022U UploadVR · demoPointed to in metaverse and VR threads as proof that realtime photorealistic face tracking from headset cameras is coming.
- 1 HN recommenders 1 months 2012–2020H Hizook · demoHN cites it as an example of what 1kHz vision and fast control loops enable, in threads about AI hardware and robotics.
- 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 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 2020–2026Cited as a vivid demonstration of the scale of Chinese state surveillance, especially in TikTok and privacy debates.
- 1 HN recommenders 1 months 2015–2026A Abe Davis's Research · demoHN commenters cite it as the classic demonstration of audio recovery from video in surveillance and privacy discussions.
- 1 HN recommenders 1 months 2021–2022Y YarrowFlower · talkHN cites it as the primary source for Tesla's vision-only reasoning, LIDAR arguments and sensor fusion challenges.
- 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 2016–2026A Ashley Feniello · demoHN mentions it as an example of voice-driven editing, and one commenter says it clarified how Vim commands compose.
- 1 HN recommenders 1 months 2012–2019HN points to it as the clearest and most striking explanation of femto-photography, with animations that make it easy to follow whenever related imaging stories appear.
- 1 HN recommenders 1 months 2020–2024HN cites it for the look of pre-car city streets, with pedestrians moving freely among carriages, and as an example of AI film restoration.
- 1 HN recommenders 1 months 2013–2024J Jack Gallant · demoHN cites it as the landmark brain-decoding demo and compares newer reconstruction work against it.
- 1 HN recommenders 1 months 2018–2020C Chen Chen · demoHN commenters flag it as a remarkable machine-learning result, notably for showing that training on raw images beats JPEG.
- 1 HN recommenders 1 months 2020–2022Pointed to as an approachable layperson's explanation whenever video magnification or vibration visualization comes up.
- 1 HN recommenders 1 months 2022–2024Cited in threads on motorcycle safety, Tesla's sensor choices and autonomous vehicles as a well-made explanation of the failure mode.
- cited 5× 0 months 2017–2026M Movietwist · comedy videoInvoked as a joke whenever AI image reconstruction or enhancement is discussed.
- cited 5× 0 months 2014–2020I Ishikawa Group Laboratory · demoCited as a vivid example of machines outpacing human reaction times and of high-speed robotic vision.
- cited 3× 0 months 2012–2020T tempura1234 · comedy videoHN uses it as shorthand for the unrealistic 'zoom and enhance' trope, in jokes about image restoration and software that claims to recover detail.
- cited 4× 0 months 2023–2025T Tom Gally · talkCited as an expert's first-hand evidence that GPT translation is near human quality for distant language pairs.
- cited 4× 0 months 2023–2025T Tom Gally · commentaryHN links it as an informed view from a working translator on using GPT for translation.
- cited 4× 0 months 2022D Dental Wings · demoPosted by an employee as a showcase of a polished desktop application, with a JavaFX UI, built by a small team.
- cited 4× 0 months 2017–2025H HBO · comedy videoMostly a running joke or reference for image-classification projects and AI app demos.
- cited 3× 0 months 2018–2020Cited as a concrete early example that AI-faked video was already convincing, in discussions of misinformation and trust in media.
- cited 4× 0 months 2019–2022HN cites it in discussions of reconstructing images from brain scans and the ethics of future brain reading.
- cited 3× 0 months 2014–2016M miaublah · comedy videoUsed as a running joke in discussions of programming by voice.
- cited 4× 0 months 2014–2024D Duncan Robson · comedy videoHN uses it as a punchline in threads about image upscaling and super-resolution, where the movie trope has become partly real.
- cited 8× 0 months 2018–2023S scrubadub1 · comedy videoCited as the classic, unintentionally hilarious example of early voice recognition failing, and of how dictation used to feel.
- cited 3× 0 months 2011–2017A AdobePhotoshopFB · demoReferenced as the original demo that stunned people when object-removal and image-inpainting algorithms come up.
- cited 5× 0 months 2019–2022N Noel N · comedy videoUsed as a joke whenever voice interfaces and accents come up, and shared as a Scottish comedy sample.
- cited 5× 0 months 2012–2018M Miki Rubinstein · demoCited as the canonical demonstration of pulling out invisible signals like pulse from video, with commenters imagining other applications.
- cited 3× 0 months 2022–2024M McLeonida · demoHN uses it as a baseline for how capable Siri seemed at launch and to argue the product has regressed since.
- cited 4× 0 months 2020–2021T The Wheel Network · news clipHN references it as evidence that pedestrian-detecting emergency braking is routinely tested by independent agencies.
- cited 5× 0 months 2020–2023B Burnistoun · comedy videoHN invokes it as the go-to joke whenever voice interfaces, speech recognition or natural-language UIs are discussed.
- cited 3× 0 months 2017–2024B Brian Roemmele · demoHN cites it as a historic demonstration of early speech synthesis, including discussions about whether the demo was genuine.
- cited 6× 0 months 2022–2025M Michael Reeves · comedy videoMostly invoked as a joke in threads about monkeys or darts beating professional stock pickers, and about loose definitions of AI.
- cited 11× 0 months 2010–2025D Duncan Robson · comedy videoUsed as a joke or critique whenever someone expects impossible image upscaling or recovery of detail.
- cited 3× 0 months 2018–2019C Channel2600 · talkHN cites it as proof that voice coding works and lists it among resources for programmers who can't type.
- cited 6× 0 months 2019–2024K Kaspars Foigts · documentaryHN commenters cite it as proof that autonomous driving was demonstrated decades before the current boom.
- cited 4× 0 months 2012–2026Q QuestVisual · demoHN brings it up as an early, impressive augmented-reality translation demo and a wow moment before modern AI.
- cited 4× 0 months 2018–2019T Tero Karras FI · demoCited as an example of how realistic GAN-generated faces had become, and of what a well-structured latent space can do.
- cited 19× 0 months 2016–2021M Matthias Niessner · demoHN uses it as a reference point in deepfake and fake-news discussions, showing that convincing real-time video manipulation was already possible in 2016.
- cited 4× 0 months 2013–2025C Colton Casados-Medve · videoUsed as the canonical reference for the 'enhance' trope whenever image upscaling or recognition comes up.
- cited 7× 0 months 2013–2023W wzamen01 · demoHN cites it as the standard example of algorithmic bias in face detection and of how skewed training data produces biased tech.
- cited 6× 0 months 2023–2025R RAINBOLT · demoCited as an early, concrete example of AI outperforming top GeoGuessr players, in threads on AI photo geolocation.
- cited 3× 0 months 2010–2014Q QiPanComputerVision · demoHN cites it as an early demo of generating 3D models just by filming an object, in threads on Kinect, 3D printing and depth cameras.
- cited 3× 0 months 2012–2018P Peter Elst · demoLinked as a memorable early demo of image deblurring whenever threads on image restoration or synthesis come up.
Questions
What is the most recommended computer vision, speech & nlp video on Hacker News?
Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning by Google TechTalks: HN commenters recommended it for years as a simple, exciting overview of the deep learning wave.
How is this computer vision, speech & nlp 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.