I tried through API with latest GPT-4-Turbo-Preview and this is what I got:
------
Let's break down the information given:
The school is two blocks north of the pool. This means if you are at the pool and move two blocks north, you'll arrive at the school.
The convenience store is one block south of the school. Therefore, if you start at the school and move one block south, you'll reach the convenience store.
Based on the first two statements, the relative positions from north to south are: School, Convenience Store, Pool.
Thus, the third statement saying "The pool is south of the convenience store" is indeed true, based on the positions provided by the first two statements.
-----
But it starts weirdly messing up, when I asked it to explain it using coordinates.
---
Let's use a simple coordinate system to represent the positions of the school, the pool, and the convenience store. Let's assume each block corresponds to one unit in this system. We'll start with the pool as our reference point at coordinates (0,0). Remember, moving north increases the y-coordinate, while moving south decreases it.
The school is two blocks north of the pool.
If the pool is at (0,0), moving two blocks north puts the school at (0, +2).
The convenience store is one block south of the school.
If the school is at (0, +2), moving one block south puts the convenience store at (0, +1).
Given these positions:
The pool is at (0, 0).
The school is at (0, +2).
The convenience store is at (0, +1).
Therefore, instead of the pool being south of the convenience store, the pool is actually located to the north of the convenience store if you consider "north" to mean increasing y-coordinates. The convenience store, being at (0, +1), is southward relative to the school but not to the pool. The pool, being at the origin point (0,0), is south of both the school and the convenience store in terms of their y-coordinates.
Thus, the third statement, "The pool is south of the convenience store," is false according to the given coordinates.
---
It gets coordinates and everything right, but still somehow messes up North and South.
Can you give an example that ChatGPT 4 doesn't get right? ChatGPT4 is much much better at logic than 3.5, it's almost laughable. It's really really impressive.
Here is ChatGPT 4s output btw:
> What is the longitude an latitude of Brussels?
Brussels, the capital city of Belgium, is located at approximately 50.8503° North latitude and 4.3517° East longitude.
> What about New York?
New York City, located in the United States, has approximate coordinates of 40.7128° North latitude and 74.0060° West longitude.
> Which one is more north?
Brussels is more north than New York City. Brussels is located at approximately 50.8503° North latitude, while New York City is at approximately 40.7128° North latitude.
I'm surprised nobody has mentioned MGRS as a somewhat similar system. Coordinates look like so; 4QFJ 1234 5678.
That means the coordinate is in the 100km grid-square named 4QFJ. At 12,340m North and 56,780m East of the SW corner.
It's easy to reason about the coordinates if they're on the same square, and given how big squares are they usually will be. You do need to memorize some letters and numbers, but since the relationships between coordinates are clear, you should only need to memorize the least-significant digits for nearby locations.
> If using built-in Points, note that the order of ll_to_earth’s coordinates is reversed: points are (x, y) which corresponds to (lng, lat). But the function takes lat, lng.
The most common error I've seen in this area is that most GIS systems use (Lat, Lng) but most systems written by non-GIS people use (Lng, Lat), which they think of as (x, y).
> 41, -73 (removed all decimals from your example location) still gives me the general location that it's somewhere in New York.
I think it would be hard to overstate how useless this data is rounded that far. 41.022755, -73.913102 is almost a two hour drive away from 41, -73 according to Google Maps, and that "drive" starts with you swimming a tenth of a mile to shore. Even if you round better (round -73.913102 to -74) we're talking about a 6.9 mile drive that will take 15 minutes. With different examples (anywhere which is close to _.5 for both coordinates, i.e. -73.5, 41.5) the distances are going to be even larger.
Rounded to two decimal points, you're at a point where the accuracy is probably good enough for most purposes, but now you're looking at 41.02, -73.91, which is clearly harder to transmit over the phone than "medium.axed.hobby".
I probably saw this too late to get a reply but: Yes, I understand that part. I don’t understand how that connects to the underlying data. Where did the x and y coordinates for each point come from? Where did the territory value of each point come from for that matter?
I'm always disappointed that these systems are so hard to reason about. Plus codes are better than hashing schemes, but still require base 20 math. It's not clear to me what they're for.
MGRS is also based on 100x100km grid squares and it just uses easting and northing from the southwest corner. e.g.
4QFJ 1234 5678 is in square 4QFJ, at 12340m east and 56780m north with 10m accuracy.
4QFJ 12341 56789 is is in square 4QFJ, at 12341m east and 56789m north with 1m accuracy.
If there's a football field roughly half a kilometre to the north, that would be 4QFJ 123 573.
At the edge of the grid square, you may define an easting or northing that exceeds the bounds of the square. That's also fine.
MGRS is a much more complicated system for computers, but humans can create new coordinates and express the precision of their location relatively easily when working in a local region.
This stuff mostly goes over my head, but I'd like to understand it. In the original method, why is op concatenating the two positions into one number, rather than just storing the lat/lon pair and using something like Euclidean distance?
This is a good example of why capturing coordinates in a local spatial reference system may be better than capturing coordinates in a global spatial reference system.
Global coordinates of a place of interest will drift relative to a global coordinate system but remain stable relative to a local coordinate system. This article illustrates that "stable" is not the same thing as unchanging in the presence of 7.5 earthquakes.
This is a really great and simple visualization, I definitely enjoyed seeing all the little dots go kerplunk :-)
One minor issue is that I think your Boston (Stoughton) store GPS coords might be wrong. Scrolling through I noticed the point was dropped in the UK somewhere, might be a confusion with Stoughton, Leicestershire.
------
Let's break down the information given:
The school is two blocks north of the pool. This means if you are at the pool and move two blocks north, you'll arrive at the school.
The convenience store is one block south of the school. Therefore, if you start at the school and move one block south, you'll reach the convenience store.
Based on the first two statements, the relative positions from north to south are: School, Convenience Store, Pool.
Thus, the third statement saying "The pool is south of the convenience store" is indeed true, based on the positions provided by the first two statements.
-----
But it starts weirdly messing up, when I asked it to explain it using coordinates.
---
Let's use a simple coordinate system to represent the positions of the school, the pool, and the convenience store. Let's assume each block corresponds to one unit in this system. We'll start with the pool as our reference point at coordinates (0,0). Remember, moving north increases the y-coordinate, while moving south decreases it.
The school is two blocks north of the pool. If the pool is at (0,0), moving two blocks north puts the school at (0, +2).
The convenience store is one block south of the school.
If the school is at (0, +2), moving one block south puts the convenience store at (0, +1).
Given these positions:
The pool is at (0, 0).
The school is at (0, +2).
The convenience store is at (0, +1).
Therefore, instead of the pool being south of the convenience store, the pool is actually located to the north of the convenience store if you consider "north" to mean increasing y-coordinates. The convenience store, being at (0, +1), is southward relative to the school but not to the pool. The pool, being at the origin point (0,0), is south of both the school and the convenience store in terms of their y-coordinates. Thus, the third statement, "The pool is south of the convenience store," is false according to the given coordinates.
---
It gets coordinates and everything right, but still somehow messes up North and South.
reply