News for hackers. Stuff that matters.
Re:'World Models,' an old idea in AI, mount a comeback by warrenm on Wednesday September 03, 2025 @03:30PM (#45119593)
you do not need to remember state with the simplest solver:

- place your right hand on the right wall - walk forward, never letting your hand leave the wall - arrive at the exit

yes, you travel many dead ends along the way

but you are guaranteed to get to the end of a 'traditional' maze

Re:'World Models,' an old idea in AI, mount a comeback by daxfohl on Wednesday September 03, 2025 @08:19PM (#45121923)
Yeah I did the type where you start somewhere inside the maze and have to find the "treasure". Mainly because it was slightly easier to implement, but also had the nice side effect of not being solvable by that rule alone.

FWIW the LLMs were definitely not following that rule. They seemed to always keep going straight whenever that was an option. Which meant they would always get stuck at T intersections when both ways led to a dead end.

Re:'World Models,' an old idea in AI, mount a comeback by warrenm on Thursday September 04, 2025 @11:03AM (#45128097)
Starting in the middle, vs one end or the other, is definitely a different problem :)