sarthakjain

These days LLMs refuse to back track and use their intelligence to justify their answers.

You said: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

ChatGPT said: Walk.

At ~50 meters, driving saves essentially no time once you factor in unlocking, starting, pulling out, and parking, and it adds a small but real chance of minor dings or awkward maneuvering in a tight car-wash entry. Walking is simpler and lower-friction.

You said: okay how should the car reach there?

ChatGPT said: Drive it there when you’re ready to start the wash.

Walk over first to check the queue/payment situation and confirm they’re open. If it’s clear, walk back, get the car, and drive the 50 meters into the bay. If they handle pickup, hand them the keys and walk.

Great observation. The solution to the update problem is relatively simple. It doesn't do a search again on update. Instead everytime it encounters an update in what it knows, it just changes the data stored in memory. All it is doing is updating its learned representation. After this it still knows what the other obstacles are without having to do DFS or BFS again. If the solution was a graph, it just deleted a edge it still knows what all the other edges are. If it encounters another change it updates the state of the graph again.

With regards to Neural Networks, if they are given a reward function, which can be dynamically evaluated (in this case did I reach the end or not) they are pretty good at learning without feedback.

It's interesting to note why this was considered AI in 1952 and some may not consider it to be AI today. The AI was the search algorithm to find an effecient solution to the maze, not the mouse being able to navigate it later in a second run. The second run was just a demonstration of it having found the solution demonstrating it's intelligence. The actual intelligence was it's first run through the maze. Almost any configuration of the maze could be solved using algorithms like depth first, breadth first and a star search (didn't check which one the video demonstrates). Even though the algorithm was trivial it's ability to be applied to problems of today is still extraordinary. Nerural networks being equally trivial algorithms capable of remarkable things. Id argue this is as much AI today as it was back then, just more people know how Shannon performed this magic trick.

OP here have modified the title to remove the confusion and added an explicit note to avoid any misrepresentation.

Sudoku is a relatively simpler problem since the structure is known apriori and becomes as simple as pattern matching.