Skip to content
0:00 / 0:00

#chatgpt#dall-e#diffusionmodels

Why ChatGPT Can't Draw a Full Glass of Wine

Alex O'Connor

2M subscribers • 1 video on Hallway

YouTube
  • Recommended by 2 people: 2 on Hacker News.
  • Presented by Alex O'Connor

Intermediate. Assumes working knowledge.

6.3M views1 year ago2 recommendations

AI and machine learningTransformers and LLMsNeural networks and deep learning

Alex O'Connor explores why AI image generators struggle to draw a wine glass filled to the brim, linking this limitation to David Hume's philosophy.

Go to piavpn.com/alex to get 83% off from our sponsor Private Internet Access with 4 months free! For early, ad-free access to videos, and to support the channel, subscribe to my Substack: alexoconnor.com To donate to my PayPal (thank you): paypal.me/cosmicskeptic - VIDEO NOTES ChatGPT can’t draw a glass of wine full to the brim. Why? And what might it have to do with David Hume and the missing shade of blue? - CONNECT My Website: alexoconnor.com SOCIAL LINKS: Twitter: twitter.com/cosmicskeptic Facebook: facebook.com/cosmicskeptic Instagram: instagram.com/cosmicskeptic TikTok: @CosmicSkeptic The Within Reason Podcast: podcasts.apple.com/gb/podcast/within-reason/id1458675168 - CONTACT Business email: contact@alexoconnor.com ------------------------------------------

Why it's here

2 people recommend this

What people say. Recommended as an excellent illustration of the limitations of generative AI models and how they map concepts.

proc0on Hacker News • Recommends

On “AI Is Already Obsolete – The Open Challenge No One Will Answer”

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 - link to 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.

jimbo808on Hacker News • Recommends

On “Getting AI to work in complex codebases”

…ations 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( link to 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).…

wavemodeon Hacker News • Mentions

On “Appeals court rules that Constitution protects possession of AI-generated CSAM”

Well, maybe. Maybe not. See "Why can't ChatGPT draw a full glass of wine?" link to 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.

kallebooon Hacker News • Mentions

On “4o Image Generation”

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 link to 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.

EGregon Hacker News • Mentions

On “Ask HN: Share your AI prompt that stumps every model”

Draw a clock that shows time other than 10:10 Draw a wine glass that's totally full to the brim etc. link to this video link