that the capabilities of LLMs have progressed dramatically in the previous few years, but it surely’s laborious to quantify simply how good they’ve develop into.
That acquired me pondering again to a geometrical drawback I got here throughout on a YouTube channel final 12 months. This was in June 2024, and I attempted to get the main giant language mannequin on the time (GPT-4o) to unravel the puzzle. It didn’t go that properly and required so much of effort to discover a resolution, and I puzzled how the newest LLMs would fare with the identical puzzle.
The puzzle
Right here’s a fast reminder of what I used to be asking the LLM to unravel again then. Assume now we have the next grid of dots/nodes. Within the x and y airplane, every node is strictly one unit away from its adjoining neighbour. It seems like this,
Now, the query I needed to reply was this,
What number of distinct squares will be drawn on this diagram?It rapidly grew to become clear that GPT-4o didn’t know the reply, so I modified tack barely and as an alternative requested it this.
I would love a Python program that plots out all of the squares we are able to
draw on the hooked up diagram, assuming that the corners of any sq.
should lie on one of many spots on the diagram. Assume every adjoining spot is
1 unit aside in each the x and y instructions. Additionally print out a abstract of
the variety of squares of the identical dimension and what their facet lengths areLengthy story quick, I finally acquired GPT-4o to give you an accurate Python-based resolution. Nonetheless, it took me round two hours and properly over 40 iterations of me going backwards and forwards with the mannequin to refine its reply till it got here up with one thing that labored.
NB, have you ever labored out the reply but? Even now, I nonetheless can’t fairly consider that it’s 21 squares you may draw on this graph.
Interplay with Sonnet 4.5
This brings us again to the current day and Anthropic’s current launch of what’s thought-about the perfect coding mannequin obtainable right now, specifically Claude Sonnet 4.5. It’s been round 16 months since I final checked out this, so simply how a lot have LLMs improved within the intervening interval? Let’s see how Sonnet 4.5 copes with the puzzle.
To make use of Sonnet 4.5, I visited Anthropic’s homepage.
You need to see a web page like this.
Click on the massive black “Attempt Claude” button positioned close to the highest proper of the display. You may be requested to log in at this level. When you don’t have already got an account with Anthropic, please set one up now. It’s utterly free to take action.
As soon as you might be logged in, you can be taken to a display displaying a well-recognized chat-based window that permits you to work together with and ask questions of Sonnet 4.5.
Earlier than I requested the mannequin to offer a Python program to unravel the puzzle, I requested it a straight query to see if it already knew the reply.
It got here again with,
Taking a look at this grid, I have to depend all potential squares of various
sizes that may be fashioned by connecting the dots.
Let me first establish the grid construction. The dots type:
2 dots within the prime row
2 dots within the second row
6 dots within the third row
6 dots within the fourth row
2 dots within the fifth row
2 dots within the sixth row
This seems to be a cross or plus-sign formed grid sample.
Now I will depend squares by dimension:
1×1 squares: These are fashioned by any 4 dots that make a unit sq..
Within the horizontal center part (rows 3-4): 5 squares per row × 1 = 5 squares
Within the vertical center part (columns the place the cross intersects): counting
the vertical segments offers us 5 extra squares
Complete: 10 small squares
2×2 squares: These want 4×4 preparations of dots.
Within the horizontal part: 4 squares
Within the vertical part: 4 squares
Overlap in middle: -1 (counted twice)
Complete: 7 squares of dimension 2×2
3×3 squares and bigger: The grid sample is barely 6 dots extensive at its most, however the cross form limits the place bigger squares can match. Checking the geometry:
One 3×3 sq. can match within the middle the place the arms of the cross overlap
Complete: 1 sq. of dimension 3×3
Complete: 10 + 7 + 1 = 18 squaresSo, confidently incorrect. Curious and intrigued in regards to the mannequin’s reference to a 3×3 sq. (which is not possible on this grid), I requested it to indicate me the sq. on the diagram. It replied with this.
Trying on the grid extra fastidiously, I have to rethink whether or not a 3×3 sq.
truly exists.
For a 3×3 sq. to exist, I would want a 4×4 association of dots
(since a 3×3 sq. requires 4 dots on all sides). Let me examine the grid
construction:
The grid seems to be:
Rows 1-2: solely 2 dots every (centered)
Rows 3-4: 6 dots every (full width)
Rows 5-6: solely 2 dots every (centered)
For a 3×3 sq., I would want 4 consecutive rows and 4 consecutive columns all with dots on the intersection factors. Nonetheless, wanting on the cross/plus sample:
The highest solely has 2 columns of dots
The center has 6 columns of dots
The underside solely has 2 columns of dots
Since rows 1-2 and rows 5-6 solely have 2 dots every (not spanning the complete width)
, there is not truly a 4×4 block of dots wherever on this grid.
I have to right my reply: There may be NO 3×3 sq. potential on this grid.
The full must be: 10 (1×1 squares) + 7 (2×2 squares) = 17 squares
I apologize for the error in my preliminary depend. The cross-shaped sample
prevents any sq. bigger than 2×2 from being fashioned.Alright, it semi-redeemed itself with that reply, however basically, it didn’t accurately say there have been 21 squares in whole.
The ultimate reply
To maintain issues truthful with the mannequin comparability over the 16 months, I requested Sonnet 4.5 the very same query I had requested GPT-4o, which, as a reminder, was this.
I would love a Python program that plots out all of the squares we are able to draw on
the hooked up diagram, assuming that the corners of any sq. should lie on one
of the spots on the diagram. Assume every adjoining spot is 1 unit aside in
each the x and y instructions. Additionally print out a abstract of the variety of
squares of the identical dimension and what their facet lengths areSonnet 4.5 thought for all of 5 seconds earlier than producing its Python code.
import matplotlib.pyplot as plt
import numpy as np
from itertools import combos
from collections import defaultdict
# Outline the grid factors based mostly on the picture
factors = [
# Top two rows (2 dots each, centered)
(3, 6), (4, 6),
(3, 5), (4, 5),
# Middle two rows (6 dots each, full width)
(1, 4), (2, 4), (3, 4), (4, 4), (5, 4), (6, 4),
(1, 3), (2, 3), (3, 3), (4, 3), (5, 3), (6, 3),
# Bottom two rows (2 dots each, centered)
(3, 2), (4, 2),
(3, 1), (4, 1),
]
def is_square(p1, p2, p3, p4):
"""Verify if 4 factors type a sq. and return facet size if true."""
factors = [p1, p2, p3, p4]
# Calculate all pairwise distances
distances = []
for i in vary(len(factors)):
for j in vary(i + 1, len(factors)):
dist = np.sqrt((factors[i][0] - factors[j][0])**2 +
(factors[i][1] - factors[j][1])**2)
distances.append(dist)
distances.type()
# For a sq.: 4 equal sides and a couple of equal diagonals
# Diagonals must be sqrt(2) occasions the facet size
if len(distances) == 6:
sides = distances[:4]
diagonals = distances[4:]
# Verify if all sides are equal
if np.allclose(sides, [sides[0]] * 4, atol=1e-6):
# Verify if diagonals are equal
if np.allclose(diagonals, [diagonals[0]] * 2, atol=1e-6):
# Verify if diagonal = facet * sqrt(2)
if np.allclose(diagonals[0], sides[0] * np.sqrt(2), atol=1e-6):
return True, sides[0]
return False, 0
def order_square_points(p1, p2, p3, p4):
"""Order factors of a sq. in counterclockwise order ranging from bottom-left."""
factors = [p1, p2, p3, p4]
# Discover centroid
cx = sum(p[0] for p in factors) / 4
cy = sum(p[1] for p in factors) / 4
# Type by angle from centroid
def angle(p):
return np.arctan2(p[1] - cy, p[0] - cx)
factors.type(key=angle)
return factors
# Discover all squares
squares = []
squares_by_size = defaultdict(listing)
for combo in combos(factors, 4):
is_sq, side_length = is_square(*combo)
if is_sq:
ordered = order_square_points(*combo)
squares.append(ordered)
squares_by_size[round(side_length, 2)].append(ordered)
# Print abstract
print("=" * 50)
print("SUMMARY OF SQUARES FOUND")
print("=" * 50)
total_squares = 0
for side_length in sorted(squares_by_size.keys()):
depend = len(squares_by_size[side_length])
total_squares += depend
print(f"Facet size {side_length}: {depend} sq.(s)")
print(f"nTotal squares: {total_squares}")
print("=" * 50)
# Create visualization
fig, axes = plt.subplots(2, 2, figsize=(14, 14))
axes = axes.flatten()
# Plot 1: All dots
ax = axes[0]
x_coords = [p[0] for p in factors]
y_coords = [p[1] for p in factors]
ax.scatter(x_coords, y_coords, c='black', s=100, zorder=3)
ax.set_xlim(0, 7)
ax.set_ylim(0, 7)
ax.set_aspect('equal')
ax.grid(True, alpha=0.3)
ax.set_title('Unique Grid', fontsize=14, fontweight='daring')
ax.set_xlabel('X')
ax.set_ylabel('Y')
# Plot 2: All squares overlaid
ax = axes[1]
ax.scatter(x_coords, y_coords, c='black', s=100, zorder=3)
colours = plt.cm.rainbow(np.linspace(0, 1, len(squares)))
for sq., colour in zip(squares, colours):
square_closed = sq. + [square[0]]
xs = [p[0] for p in square_closed]
ys = [p[1] for p in square_closed]
ax.plot(xs, ys, c=colour, linewidth=2, alpha=0.6)
ax.set_xlim(0, 7)
ax.set_ylim(0, 7)
ax.set_aspect('equal')
ax.grid(True, alpha=0.3)
ax.set_title(f'All {total_squares} Squares Overlaid', fontsize=14, fontweight='daring')
ax.set_xlabel('X')
ax.set_ylabel('Y')
# Plot 3 & 4: Squares by dimension
plot_idx = 2
for side_length in sorted(squares_by_size.keys()):
if plot_idx >= len(axes):
break
ax = axes[plot_idx]
ax.scatter(x_coords, y_coords, c='lightgray', s=100, zorder=2)
squares_of_size = squares_by_size[side_length]
colours = plt.cm.viridis(np.linspace(0, 1, len(squares_of_size)))
for sq., colour in zip(squares_of_size, colours):
square_closed = sq. + [square[0]]
xs = [p[0] for p in square_closed]
ys = [p[1] for p in square_closed]
ax.plot(xs, ys, c=colour, linewidth=2.5, marker='o', markersize=8)
ax.set_xlim(0, 7)
ax.set_ylim(0, 7)
ax.set_aspect('equal')
ax.grid(True, alpha=0.3)
ax.set_title(f'Squares with facet size {side_length} ({len(squares_of_size)} whole)',
fontsize=14, fontweight='daring')
ax.set_xlabel('X')
ax.set_ylabel('Y')
plot_idx += 1
plt.tight_layout()
plt.present()At first sight, I believed there was no method Sonnet might have give you an accurate resolution so rapidly. GPT-4o had taken hours. Nonetheless, I put in all of the required libraries the code wanted and copied and pasted it right into a Jupyter Pocket book cell, operating it and acquiring the next output. I’ve omitted the graphs for now, which have been additionally output.
==================================================
SUMMARY OF SQUARES FOUND
==================================================
Facet size 1.0: 9 sq.(s)
Facet size 1.41: 4 sq.(s)
Facet size 2.24: 2 sq.(s)
Facet size 2.83: 4 sq.(s)
Facet size 3.61: 2 sq.(s)
Complete squares: 21
==================================================
#
# Plus some graphs that I am not exhibiting right here
#That shocked me. The reply was completely spot on.
The one slight factor the mannequin didn’t fairly get proper was that it didn’t output a plot of every set of otherwise sized squares. It simply did the 9 1x1s and the 4 √2x√2 ones. I solved that by asking Sonnet to incorporate these, too.
Are you able to print the graphs in sq. facet order. Can also you may have two graphs
facet by facet on every "line"That is what it produced.
Stunning.
Abstract
To reveal simply how dramatically LLMs have superior in a couple of 12 months, I made a decision to revisit a difficult geometric puzzle I first tried to unravel with GPT-4o again in June 2024. The puzzle was to jot down a Python program that finds and plots all potential squares on a selected cross-shaped grid of dots.
My expertise somewhat over a 12 months in the past was a battle; it took me roughly two hours and over 40 prompts to information GPT-4o to an accurate Python resolution.
Quick ahead to right now, and I examined the brand new Claude Sonnet 4.5. Once I first requested the mannequin the query instantly, it did not calculate the right variety of squares. Not a fantastic begin, nonetheless, the actual take a look at was giving it the very same immediate I used on GPT-4o.
To my shock, it produced an entire, right Python resolution in one shot. The code it generated not solely discovered all 21 squares but in addition accurately categorised them by their distinctive facet lengths and generated detailed plots to visualise them. Whereas I wanted one fast follow-up immediate to excellent the plots, the core drawback was solved immediately.
Might or not it’s that the very act of my attempting to unravel this puzzle final 12 months and publishing my findings launched it to the web-o-sphere, that means Anthropic have merely crawled it and integrated it into their mannequin data base? Sure, I suppose that could possibly be it, however then why couldn’t the mannequin reply the primary direct query I requested it in regards to the whole variety of squares accurately?
To me, this experiment starkly illustrates the unbelievable leap in LLM functionality. What was as soon as a two-hour iterative battle with the main mannequin of its time 16 months in the past is now a five-second, one-shot success with the main mannequin right now.
