HackerTubewatch
Surprise me
Frame from Computer program that learns to play classic NES games Plays via YouTube's privacy-enhanced embed

Computer program that learns to play classic NES games

11 videos recommended on HN
YouTube
9 HN users recommended this demo10 months2015–2025 score 11
Years with an HN recommendation, 2007–2026

Loved on HN as a hilarious, brilliant example of hacker-academic work and cited whenever game-playing AI or fuzzing comes up.

Tom7 explains and demos software that learns to play NES games by finding score patterns in memory and then searching for inputs that raise it. It is the video companion to his SIGBOVIK paper.

“Watch the whole thing, it's delightful.” (HN, 2021)

2 strong recommendations · 8 recommendations · 8 citations · 1 jokes · Demos

19 Hacker News comments

From the HN archive; up to 20 kept per video, favoring different commenters. Recommendations first.

@fartcannon Feb 2021 Strongly recommends
on HN thread Medical chatbot using OpenAI’s GPT-3 told a fake patient to kill themselves
There was an AI created the absolutely brilliant Tom7 on on his YouTube channel 'SuckerPinch' on April 1, 2013 that paused a game of Tetris instead of losing. In my opinion, Tom doesn't get enough credit for his work. He released his AI a full 8+ months before DeepMind released their Atari playing AI. Watch the whole thing, it's delightful. The AI pauses Tetris right before it loses at around 16mins into the video. [this video] I also recommend his other videos. Brilliant guy. Edit: Here's the paper [link]
AI that paused Tetris before losing, predating DeepMind Atari.
@recondite Mar 2015 Recommends
on HN thread SIGBOVIK 2015 Proceedings [pdf]
Haha, I love it. There was a SIGBOVIK submission a couple years ago that looked at byte patterns within video game RAM (specifically NES) to automate the playing of. Pretty entertaining stuff. [this video]
Entertaining automated NES playing from RAM byte patterns.
@fixermark Apr 2016 Recommends
on HN thread Automatic 3Dification of Nintendo Games: The GlEnd() of Zelda
Tom 7's work on machine learning and NES emulation is very impressive. This isn't the first time he's attacked that space; you can see previous experiences he had with an automatic game-playing AI he built called "LearnFun / PlayFun" on that YouTube channel also: [this video] [link] [link]
Tom7's LearnFun/PlayFun game-playing AI.
@tomjakubowski May 2016 Recommends
on HN thread Autonomous Mini Rally Car Teaches Itself to Powerslide
If you're interested in a "dumber" approach to machines "learning" to play classic video games (including Super Mario Bros), tom7's video [1] and paper [2] on Playfun are both fascinating. [1] [this video] [2] [link]
Dumber approach to machines learning to play games.
@onli Apr 2017 Recommends
on HN thread The glEnd of Zelda(): Automatic 3Dification of NES Games (2016)
You should look at some other things the author did. They fit in the same area of craziness, and are absolutely great. For example [link] , Portmantout: A portmanteau of every English word, or the first one, [this video] , Computer program that learns to play classic NES games. I also liked the humor in What, if anything, is epsilon?, [link] .
One of the author's crazy and great projects.
@onli Jun 2018 Recommends
on HN thread Reverse-emulating the NES
I'm not sure many people can pull this off. The author here was also great in his presentation about automated NES playing, [this video] . You don't see often academics & hacker work that is also combined with the right amount of humor. He even 3Dified the original Zelda!
Academic hacker presentation on automated NES playing with humor.
@dan_quixote Oct 2022 Recommends
on HN thread MAR1D: First-Person Mario
tom7 is awesome. He made an awesome and hilarious video years ago about his SIGBOVIK paper/research on AI playing NES: [this video]
Hilarious video on SIGBOVIK NES-playing AI research.

Citations, criticism and jokes

@Karunamon Nov 2015 Cites it
on HN thread Classic Nintendo Games Are NP-Hard (2012)
So as someone with only a lay understanding of what NP-Hard means - does anyone remember that neural network that someone trained to play the game[1]? So if you can train a neural network to solve an NP-Hard problem, does that mean by definition (since NP refers to a whole class of problems) that a neural network could eventually be trained to solve any given NPH problem given the time and compute resources to do so? [1]: [this video]
@Houshalter Jun 2017 Cites it
on HN thread Why I’m Remaking OpenAI Universe
Read more
Why not use game emulators? With popular NES emulators you can advance the game frame by frame. You can read the raw memory addresses that correspond to the score. You can dump the memory at any time and reload the game to a specific game state. You can even manipulate the games in many fun ways by messing around with the game memory. Or give an AI algorithm access to memory addresses as additional information, instead of relying on pure machine vision, if you want to do that.. Here's an example of a guy who made a general game playing algorithm that brute forces it's way through any NES game: [this video] This isn't necessarily interesting from an AI perspective - the playing algorithm is just brute force. But it shows what can be done with the platform, easily reloading to previous states and exploring counterfactual futures (which is exactly the sort of thing RL algorithms do.) He also has a cool algorithm for finding the objective function of an arbitrary game, by watching a human play, and seeing what memory addresses increment. Which is a lot more easy to use than writing OCR code to read the score and game over states from the screen.
Brute-force general NES playing using memory access.
@djsumdog Dec 2017 Cites it
on HN thread Classic Nintendo Games Are NP-Hard (2012)
Here is an actual implementation of trying to implement a general AI to play all NES games. It's pretty interesting, but his approach does involve the algorithm having access to the raw NES memory map: [this video]
General AI playing NES games using raw memory.
@dpflan Mar 2018 Cites it
on HN thread AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code
This reminds me of AI research using NES Games. The AI eventually became proficient at completing Mario levels, and along the way it discovered novel strategies for survival, obtaining points, and finishing levels. > Check out this timestamp to watch the machine "cheat": [this video] > Researcher's site about the project: [link] > The Paper: The First Level of Super Mario Bros. is Easy with Lexicographic Orderings and Time Travel...after that it gets a little tricky. : [link]
AI discovers novel strategies in NES Mario.
@chc4 Apr 2024 Cites it
on HN thread How Antithesis finds bugs
A lot of fuzzers use Mario or other simple games as an internal testcase. I'm aware of a hypervisor fuzzer from 2016 that did it, and I'm positive there are others (both before and since). Hell, tom7 has a fuzzer for exploring program states that uses Super Mario Bros as the example from 2013 ( [link] , plus a youtube video [this video] ), and he's definitely not the first either.
Early example of fuzzer exploring Super Mario states.
@MrPoush May 2024 Cites it
on HN thread Reversing Choplifter
Tom7 implemented some of this with his Learnfun and Playfun ( [this video] ) - It looks for lexicographical changes to bytes in memory (i.e., one byte seems to almost always increase, and then when it suddenly decrements, a neighboring byte is incremented) as a way of calculating memory location for increasing values (score, x-position), and similarly detects bytes that generally seem to decrease (lives). It then tries to play the game, choosing inputs that increase the values that should be increasing (move right, gain lives), or tries not to decrease the values that are decreasing (don't die).
Explains how LearnFun finds score and lives bytes in memory.
@Dwedit Aug 2025 Cites it
on HN thread Optimizing our way through Metroid
Did anyone else get reminded of the Lexographic Ordering Solver that played NES games? This was featuring in Sigbovik 2013. [link] Video: [this video]
Lexicographic ordering solver playing NES games.
@keeperofdakeys Aug 2025 Makes a joke
on HN thread We put a coding agent in a while loop
A bit out of context, but it reminded me of this funny moment. The only winning move is not to play. [this video] (Background: Someone training an algorithm to win NES games based on memory state)

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.

Keyboard shortcuts

/
Search
j k
Next / previous video
r
Surprise me
l
Like (video page)
w
Watch later (video page)
?
This help
Esc
Close