Hacker News Reader

As I mentioned in the other post, the curiosity bots can help with this.

They're rewarded by exploring, not by values in game.

Maybe alone they're not enough, but in conjunction with other things, I bet we could beat Zelda. I had the bot exploring enough to find the first dungeon of LoZ.

View on HN

I just took a look at the curiosity video. It's funny, I think with enough refinement something like this could beat Zelda. Except it wouldn't actually know it beat the game! I feel like that is cheating, somehow.

Like maybe you could get American Fuzzy Lop [1] to beat Zelda. Isn't that the same thing, in principle?

[1] http://lcamtuf.coredump.cx/afl/

AFL might eventually get lucky, but I'm guessing you'd want a hybrid approach that combines symbolic execution with a fuzzer like AFL, e.g. QSYM [1].

[1] https://www.usenix.org/system/files/conference/usenixsecurit...

Reply on news.ycombinator.com