2 HN users recommended this explainer2 months2025score 2
Years with an HN recommendation, 2007–2026
HN treats it as the origin of the full-wine-glass meme and an illustration of how models lack concepts missing from their training data.
Alex O'Connor shows that ChatGPT cannot draw a wine glass filled to the brim, and ties the failure to David Hume's missing shade of blue. It asks what the failure says about how image models learn.
“this video is where the "AI can't draw a full glass of wine" meme got traction” (HN, 2025)
I completely agree. You can see this limitation if you try to create anything complex with the current state of the art. There is also a great video by Alex O'Connor on a simple prompt to generate a full glass of wine, which illustrates this really well - [this video] This wave of AI is amazing. It's a great tool for many applications, and it will even revolutionize many of them, but it is still far from AGI, a term that has been hijacked by the tech industry to hype up their products. In some ways AI has advanced a lot, but in other ways it has been set back by the hype and muddying of the terms.
Shows ChatGPT failing to draw a full wine glass, illustrating AI limits.
I think you're looking at it too abstractly. An LLM isn't representing anything, it has a bag of numbers that some other algorithm produced for it. When you give it some numbers, it takes them and does matrix operations with them in order to randomly select a token from a softmax distribution, one at a time, until the EOS token is generated. If they don't have any training data that covers a particular concept, they can't map it onto a world model and make predictions about that concept based on an understanding of the world and how it works. [This video]( [this video] ) illustrates it pretty well. These things may or may not end up being fixed in the models, but that's only because they've been further trained with the specific examples. Brains have world models. Cats see a cup of water, and they know exactly what will happen when you tip it over (and you can bet they're gonna do it).
Illustrates that models lack world models for concepts missing from training data.
Well, maybe. Maybe not. See "Why can't ChatGPT draw a full glass of wine?" [this video] Diffusion models do posses some capability to synthesize ideas, but that capability does not necessarily generalize to every possible use case. So it's impossible to say for certain that that is what is happening.
Example of diffusion models failing to generalize to a full wine glass.
I think you're missing the context everyone else has - this video is where the "AI can't draw a full glass of wine" meme got traction [this video] The prompts (some generated by ChatGPT itself, since it's instructing DALL-E behind the scenes) include phrases like "full to the brim" and "almost spilling over" that are not up to interpretation at all.
Origin of the full wine glass AI meme, with explicit prompts failing.
Video list and Hacker News comment labels from HackerTube (prompted by @karpathy), released under ODC-By 1.0, built on the open-index/hacker-news archive. Hacker News data is provided by Y Combinator; comments remain the work of their authors. Video titles, channel names and thumbnails belong to their creators and are shown via YouTube. HackerTube Watch is an unofficial edition. Data export of 2026-10-31.
Plays via YouTube's privacy-enhanced embed
5 Hacker News comments
From the HN archive; up to 20 kept per video, favoring different commenters. Recommendations first.
Read more
Citations, criticism and jokes