Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code

theverge.com

Post reply on HN
Print view View original

21–30 of 47 posts

Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code

#21

Post by PeterisP »

pvg wrote: post #18
andyjohnson0 wrote: post #14

The title seems misleading to me. The AI isn't finding bugs by somehow examining the game's source code, it's trying random gameplay and exploiting any advantages that emerge. That it's finding previously unknown bugs seems to be almost entirely down to trying things that human players wouldn't think to do.

The AI isn't finding bugs by somehow examining the game's source code The title doesn't say that.

It kind of implies that - "AI Cheats at Old Atari Games by Finding Unknown Bugs" would be an accurate title, but the extended "AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code" tells that it's actually finding something in the code, as opposed to simply unexpected/emergent behavior.

Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code

#22

Post by corobo »

PeterisP wrote: post #21
pvg wrote: post #18

Earlier quoted context omitted.

The AI isn't finding bugs by somehow examining the game's source code The title doesn't say that.

It kind of implies that - "AI Cheats at Old Atari Games by Finding Unknown Bugs" would be an accurate title, but the extended "AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code " tells that it's actually finding something in the code, as opposed to simply unexpected/emergent behavior.

I read it and presume it's meant to be read as the AI finding "unknown [bugs in the code]" as opposed to "unknown [bugs] in the code"

Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code

#23

Post by montyf »

andyjohnson0 wrote: post #14

The title seems misleading to me. The AI isn't finding bugs by somehow examining the game's source code, it's trying random gameplay and exploiting any advantages that emerge. That it's finding previously unknown bugs seems to be almost entirely down to trying things that human players wouldn't think to do.

Exactly what I was thinking. It may be a bug, but the AI treats it as another legitimate game rule. I wonder if there are any techniques for it to be able to tell the difference... for example, if it can quantitatively demonstrate that the conditions for a rule are very rare/unlikely.

Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code

#24

Post by corobo »

camgunz wrote: post #20

Can we put AI to work on proving that we live in a simulation? I would never enter/exit my apartment 38 times alternating between forwards, backwards and each side, but an AI would. Maybe then all the walls start flashing and then we'll know!

"AI, are you in a simulation?" "Yes" "no I don't mean.. not the simulation I'm running you in, outside of that"

Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code

#25

Post by pbhjpbhj »

dpflan wrote: post #10

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": https://youtu.be/xOCurBYI_gY?t=9m55s > Researcher's site about the project: http://www.cs.cmu.edu/~tom7/mario/ > The Paper: The First Level of Super…

Lol, that Youtube video, at the end the AI pauses the game of Tetris forever so as not to lose.

Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code

#26

Post by dpflan »

pbhjpbhj wrote: post #25
dpflan wrote: post #10

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": https://youtu.be/xOCurBYI_gY?t=9m55s > Researcher's site about the project: http://www.cs.cmu.edu/~tom7/mario/ > The Paper: The First Level of Super…

Lol, that Youtube video, at the end the AI pauses the game of Tetris forever so as not to lose.

Agreed, that may be the cleverest thing the AI did.

Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code

#27

Post by atldev »

iforgotpassword wrote: post #13
dpflan wrote: post #10

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": https://youtu.be/xOCurBYI_gY?t=9m55s > Researcher's site about the project: http://www.cs.cmu.edu/~tom7/mario/ > The Paper: The First Level of Super…

This guy. One of my favorite YouTube channels. Releases something like once a year but oh boy, worth the wait. Check it out if you're a nerd and like creative/useless stuff. ;)

Well worth the watch. His quote when the AI pauses the game is gold!

Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code

#28

Post by ballenf »

dpflan wrote: post #10

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": https://youtu.be/xOCurBYI_gY?t=9m55s > Researcher's site about the project: http://www.cs.cmu.edu/~tom7/mario/ > The Paper: The First Level of Super…

Speaking of easy, I spent many an hour playing that Qbert version on Atari and a decent number of quarters spent on the arcade version.

The atari version even on the hard setting was almost fatally dumbed down to be mindless. The enemies were just way dumber than in the arcade version. The game really didn't even feel like Qbert.

With just a little practice, one could play on a single life for as long as desired. Similar to Asteroids on Atari.

Re: AI Cheats at Old Atari Games by Finding Unknown Bugs in the Code

#29

Post by maxander »

pbhjpbhj wrote: post #25
dpflan wrote: post #10

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": https://youtu.be/xOCurBYI_gY?t=9m55s > Researcher's site about the project: http://www.cs.cmu.edu/~tom7/mario/ > The Paper: The First Level of Super…

Lol, that Youtube video, at the end the AI pauses the game of Tetris forever so as not to lose.

Another case where “the winning move is not to play.”
Post reply on HN