An interesting test in this vein that I read about in a comment on here is generating a 13 hour clock—I tried just about every prompting trick and clever strategy I could come up with across many image models with no success. I think there's so much training data of 12 hour clocks that just clobbers the instructions entirely. It'll make a regular clock that skips from 11 to 13, or a regular clock with a plaque saying "13 hour clock" underneath, but I haven't gotten an actual 13 hour clock yet.

If you want to see something rather amusing - instead of using the LLM aspect of Gemini 3.0 Pro, feed a five-legged dog directly into Nano Banana Pro and give it an editing task that requires an intrinsic understanding of the unusual anatomy.

  Place sneakers on all of its legs.

https://imgur.com/a/wXQskhL

I had no trouble getting it to generate an image of a five-legged dog first try, but I really was surprised at how badly it failed in telling me the number of legs when I asked it in a new context, showing it that image. It wrote a long defense of its reasoning and when pressed, made up demonstrably false excuses of why it might be getting the wrong answer while still maintaining the wrong answer.

Its not that they aren’t intelligent its that they have been RL’d like crazy to not do that

Its rather like as humans we are RL’d like crazy to be grossed out if we view a picture of a handsome man and beautiful woman kissing (after we are told they are brother and sister) -

Ie we all have trained biases - that we are told to follow and trained on - human art is about subverting those expectations

Isn't this proof that LLMs still don't really generalize beyond their training data?

Do 7 legged dog. Game over.

It's not obvious to me whether we should count these errors as failures of intelligence or failures of perception. There's at least a loose analogy to optical illusion, which can fool humans quite consistently. Now you might say that a human can usually figure out what's going on and correctly identify the illusion, but we have the luxury of moving our eyes around the image and taking it in over time, while the model's perception is limited to a fixed set of unchanging tokens. Maybe this is relevant.

(Note I'm not saying that you can't find examples of failures of intelligence. I'm just questioning whether this specific test is an example of one).

I just oneshot it with claude code (opus 4.5) using this prompt. It took about 5 mins and included detecting that it was cheating at first (drew a line around the boundary of the maze instead), so it added guardrails for that:

```

Create a devenv project that does the following:

  - Read the image at maze.jpg
  - Write a script that solves the maze  in the most optimal way between the mouse and the cheese
  - Generate a new image which is of the original maze, but with a red line that represents the calculated path

```

  Output: https://gist.github.com/J-Swift/ceb1db348f46ba167948f734ff0fc604  
  Solution: https://imgur.com/a/bkJloPT

I kinda want to know what happens if you make it continue the line by one step 20 times in a row. A human can draw this gradually, the image model has to draw it in one shot all at once.

In fact, one of the tests I use as part of GenAI Showdown involves both parts of the puzzle: draw a maze with a clearly defined entrance and exit, along with a dashed line indicating the solution to the maze.

Only one model (gpt-image-1) out of the 18 tested managed to pass the test successfully. Gemini 3.0 Pro got VERY close.

https://genai-showdown.specr.net/#the-labyrinth

I have also tried the maze from a photo test a few times and never seen a one-shot success. But yesterday I was determined to succeed so I allowed Gemini 3 to write a python gui app that takes in photos of physical mazes (I have a bunch of 3d printed ones) and find the path. This does work.

Gemini 3 then one-shot ported the whole thing (which uses CV py libraries) to a single page html+js version which works just as well.

I gave that to Claude to assess and assign a FAANG hiring level to, and it was amazed and said Gemini 3 codes like an L6.

Since I work for Google and used my phone in the office to do this, I think I can't share the source or file.

I tried this with Claude:

``` > [Image #1] Create a unicode "ascii-art" version of this image, with the optimal path through the maze highlighted in a solid colour.

I'll create an ASCII art version of this maze with the solution path highlighted!

  ┌─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┐
  ●●│ │ │ │       │   │       │     │ │   │   │ │ │   │
  ├─┤●└─┴─┐ ├───┐ │ ╔═╗ ├─────┤ ╔═══╝ │ ╔═╝ ╔═╝ │ │ ╔═╝ ├─┤
  │ │●●●●●└─┤   │ │ ║ │ │     │ ║     │ ║   ║   │ │ ║   │ │
  │ └───┐●╔═╧═╗ │ └─╢ │ │ ┌─╔═╝ ║ ┌───┤ ╚═╗ ╚═╗ │ └─╢ ┌─┘ │
  │     │●║   ║ │   ║ │ │ │ ║   ║ │   │   ║   ║ │   ║ │   │
  ├───┐ │●╚═╗ ╚═╧═╗ ║ └─┤ │ ║ ╔═╝ └─╔═╧═╗ ╚═╗ ╚═╧═╗ ║ └─┬─┤
  │   │ │●●●└───┐ ║ ║   │ │ ║ ║     ║   ║   ║     ║ ║   │ │
  │ ╔═╝ └───┐●╔═╝ ║ ╚═╗ │ └─╢ ╚═╗ ╔═╝ ╔═╝ ┌─╢ ╔═══╝ ╚═╗ │ │
  │ ║       │●║   ║   ║ │   ║   ║ ║   ║   │ ║ ║       ║ │ │
  │ ╚═══╗ ╔═╝●╚═╗ ╚═╗ ║ ├─╔═╧═╗ ║ ║ ╔═╝ ╔═╝ ║ ║ ╔═╗ ╔═╝ │ │
  │     ║ ║●●●●●│   ║ ║ │ ║   ║ ║ ║ ║   ║   ║ ║ ║ ║ ║   │ │
  ├───╔═╝ ║●┌─┐●└─╗ ║ └─┤ ║ ╔═╝ ║ ╚═╝ ╔═╧═╗ ║ ╚═╝ ║ ╚═╗ │ │
  │   ║   ║●│ │●●●║ ║   │ ║ ║   ║     ║   ║ ║     ║   ║ │ │
  │ ╔═╝ ╔═╝●│ └─┐●╚═╧═╗ │ ║ ║ ╔═╧═══╗ ║ ╔═╝ ╚═══╗ ╚═╗ ║ └─┤
  │ ║   ║●●●│   │●●●●●║ │ ║ ║ ║     ║ ║ ║       ║   ║ ║   │
  │ ║ ╔═╝●┌─┴─╗ └───┐●╚═╝ ║ ║ ║ ╔═╗ ║ └─╢ ╔═══╗ ╚═╗ ╚═╝ ╔═╝
  │ ║ ║●●●│   ║     │●●●●●║ ║ ║ ║ ║ ║   ║ ║   ║   ║     ║
  │ ╚═╝●╔═╧═╗ ╚═╗ ╔═╧═══┐●╚═╝ ║ ║ ║ ╚═╗ ║ ║ ╔═╧═╗ ╚═══╗ ╚═╗
  │   ●●║   ║   ║ ║     │●●●●●║ ║ ║   ║ ║ ║ ║   ║     ║   ║
  ├─╔═┘●╚═╗ ╚═╗ ║ ║ ╔═╗ └───┐●╚═╝ ╚═╗ ║ └─╢ ║ ╔═╧═╗ ╔═╝ ╔═╝
  │ ║●●●●●║   ║ ║ ║ ║ ║     │●●●●●●●║ ║   ║ ║ ║   ║ ║   ║
  │ ║●┌─╗ ╚═╗ ║ └─╢ ║ ╚═══╗ └─────┐●╚═╧═╗ ║ ║ ║ ╔═╝ ║ ╔═╝ ╔
  │ ║●│ ║   ║ ║   ║ ║     ║       │●●●●●║ ║ ║ ║ ║   ║ ║   ║
  │ ╚═╝ ║ ╔═╝ ╚═╗ ║ ╚═╗ ╔═╧═════╗ └───┐●╚═╝ ║ ╚═╝ ╔═╝ ║ ╔═╝
  │     ║ ║     ║ ║   ║ ║       ║     │●●●●●║     ║   ║ ║
  └─────╨─╨─────╨─╨───╨─╨───────╨─────┴───●●╨─────╨───╨─╨──

  The path from the mouse () to the cheese () is marked with ● characters. This shows the optimal route through the maze, navigating through the corridors while avoiding all the walls!

Suffice to say, it didn't do either part right.

That might be an interesting training set, a bunch of mazes…

The reason is that image generators don't iterate on the output in the same way the text-based LLMs do. Essentially they produce the image in "one hit" and can't solve a complex sequence in the same way you couldn't one-shot this either. Try taking a random maze, glance at it, then go off to draw a squiggle on a transparency. If you were to place that on top of the maze, there's virtually no chance that you'd have found the solution on the first try.

That's essentially what's going on with AI models, they're struggling because they only get "one step" to solve the problem instead of being able to trace through the maze slowly.

An interesting experiment would be to ask the AI to incrementally solve the maze. Ask it to draw a line starting at the entrance a little ways into the maze, then a little bit further, etc... until it gets to the end.

Google's summary of the thinking process isn't as detailed or accurate as what is actually being thought out.

For instance, look at what other reasoning models show you about their thinking. You can tell Gemini is not giving it all to you, so I don't put full trust in it unless it routinely is giving me an issue that I can catch in there.

For instance, it doesn't show you all the tool use that it can use nor distinguish the different types where I really wish it would. Especially because I force it to in a Gemini personal context instruction as well as many prompts and it does do them

The marketing of these products is intentionally ignorant of how LLM cognition differs from human cognition.

Let's not say that the people being deceptive are the people who've spotted ways that that is untrue...

I thought adversarial testing like this was a routine part of software engineering. He's checking to see how flexible it is. Maybe prompting would help, but it would be cool if it was more flexible.

This is the first time I hear the term LLM cognition and I am horrified.

LLMs don‘t have cognition. LLMs are a statistical inference machines which predict a given output given some input. There are no mental processes, no sensory information, and certainly no knowledge involved, only statistical reasoning, inference, interpolation, and prediction. Comparing the human mind to an LLM model is like comparing a rubber tire to a calf muscle, or a hydraulic system to the gravitational force. They belong in different categories and cannot be responsibly compared.

When I see these tests, I presume they are made to demonstrate the limitation of this technology. This is both relevant and important that consumers know they are not dealing with magic, and are not being sold a lie (in a healthy economy a consumer protection agency should ideally do that for us; but here we are).

https://gemini.google.com/share/8cef4b408a0a

Surprisingly, it got all of them right

It mostly depends on "how" the models work. Multi-modal unified text/image sequence to sequence models can do this pretty well, diffusion doesn't.

I just re-ran that image through Gemini 3.0 Pro via AI Studio and it reported:

  I've moved on to the right hand, meticulously tagging each finger. After completing the initial count of five digits, I noticed a sixth! There appears to be an extra digit on the far right. This is an unexpected finding, and I have counted it as well. That makes a total of eleven fingers in the image.

That's okay. Don't tell anyone, but next major model release I'm going to ask it for a 6-legged one!

So much this. People don't realize that when 1 trillion (10 trillion, 100 trillion, whatever comes next) is at stake, there are no limits what these people will do to get them.

I will be very surprised if there are not at least several groups or companies scraping these "smart" and snarky comments to find weird edge cases that they can train on, turn into demo and then sell as improvement. Hell, they would've done it if 10 billion was at stake, I can't really imagine (and I have vivid imagination, to my horror) what Californian psychopaths can do for 10 trillion.

Sounds like they used GenAI to make them. The "Editor" models (Seedream, Nano-Banana) can easily integrate a fifth limb to create the "dog with awkward walking animation".

https://imgur.com/a/wXQskhL

Go watch some of the more recent Google developer, Google AI, and Google deepmind videos, they're all separate channels at YouTube but try to catch some from the last 6 months with some of these explanatory topics on the developer side that are philosophical/ mathematical enough to explain this to you without going into the gritty details and should answer your question

I think we are too quick to discount the possibility that this flaw is slightly intentional, in the sense that the optimization has a tight budget to work with (equivalent of ~3000 tokens) so why would it waste capacity on this when it could improve capabilities around reading small text in obscured images? Sort of like humans have all these rules of thumbs that backfire in all these ways but that's the energy efficient way to do things.