Readit Newssarthakjain commented on Claude Shannon Demonstrates Machine Learning (1952) techchannel.att.com/play-... · Posted by u/jchallis
>> 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.
But that's not the whole story! The program can update its solution of the maze when the maze changes, but it is capable of only changing that part of the solution that has actually changed. When Shannon changes the maze and places Theseus in the modified part of the maze, I kind of rolled my eyes, sure that it was going to start a new search, all over again, but I was wrong: it searches until it finds where the unmodified part of the maze begins, then it continues on the path it learned before.
It seems that, in solving the maze, the program is building some kind of model of its world, that it can then manipulate with economy. For comparison, neural nets cannot update their models - when the world changes, a neural net can only train its model all over again, from scratch, just like I thought Theseus would start a whole new search when Shannon changed the maze. And neural nets can certainly not update parts of their models!
This demonstration looks primitive because everything is so old (a computer made with telephone relays!), but it's actually attacking problems that continue to tie AI systems of today into knots. It is certainly AI. And, in "early 1950's", it's AI avant la lettre.
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.
sarthakjain commented on Claude Shannon Demonstrates Machine Learning (1952) techchannel.att.com/play-... · Posted by u/jchallis
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.
sarthakjain commented on Applying Apple's Framework for Avoiding Mediocrity sarthakjain.com/p/apples-... · Posted by u/sarthakjain
OP here have modified the title to remove the confusion and added an explicit note to avoid any misrepresentation.
And indeed, Sonnet and Opus 4.5 (medium reasoning) say the following:
Sonnet: Drive - you need to bring your car to the car wash to get it washed!
Opus: You'll need to drive — you have to bring the car to the car wash to get it washed!
Gemini 3 Pro (medium): You should drive.
--
But OpenAI 5.2 reasoning, even at high, told me to walk. My first instinct was, I had underspecified the location of the car. The model seems to assume the car is already at the car wash from the wording. GPT 5.x series models behave a bit more on the spectrum so you need to tell them the specifics. So I asked:
"I want to wash my car. My car is currently at home. The car wash is 50 meters away. Should I walk or drive?"
GPT 5.2 Reasoning (medium):
"Drive—your goal is to get the car to the car wash, and it’s only 50 meters, so a slow, careful drive is simplest.
One small optimization: if you’re worried about starting the car for such a short trip or you want to avoid idling in a line, you can walk over first to check if there’s a queue / if it’s open, then come back and drive the car over when it’s your turn."
Which seems to turn out as I expected.
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.