Re:I failed to recreate the 1996 Space Jam Website with Claude
by Wowfunhappy on Sunday December 07, 2025 @04:24PM
(#46185301)
Interesting thought. I wonder if Anthropic et al could include some sort of render-html-to-screenshot as part of the training routine, such that the rendered output would get included as training data.
[ Parent
| on HN ]
Re:I failed to recreate the 1996 Space Jam Website with Claude
by btown on Sunday December 07, 2025 @06:02PM
(#46186254)
Even better, a tool that can tell the rendered bounding box of any set of elements, and what the distances between pairs of elements are, so it can make adjustments if relative positioning doesn't match its expectation. This would be incredible for SVG generation for diagrams, too.
Re:I failed to recreate the 1996 Space Jam Website with Claude
by KaiserPro on Sunday December 07, 2025 @05:47PM
(#46186090)
thats basically a VLM, but the problem is that describing the world requires a better understanding of the world. Hence why LeCunn is talking about world models (Its also cutting edge for teaching robots to manipulate and plan manipulations)