pixels

2 statements across 2 episodes · 1 bullish · 0 bearish · 2 people on the record · first statement Nov 25, 2025 by Justin Johnson · across every show →

Everything said about pixels, oldest first

Nov 25, 2025 bullish
Insight
Johnson: Pixels offer a more lossless world representation than tokenized text
“And then like you actually lose something if you translate to this like purely tokenized representations that we use in LLMs, right? Like you lose the font, you lose the line breaks, you lose sort of the two D arrangement on the page. And for a lot of cases, f…”
Justin Johnson Nov 25, 2025 ▶ 22:11 After LLMs: Spatial Intelligence and World Models — Fei-Fei Li & Justin Johnson, World Labs
Jun 1, 2026 neutral
Insight
Ethan He: Training transformers directly on raw image pixels is impossible
“If you're trying, if you can technically, theoretically train image or video models on pure pixels, but the problem is that the, it's a lot of tokens. So like one image, like it's a thousand by a thousand is like one million tokens, one million pixels. It's im…”
Ethan He Jun 1, 2026 ▶ 15:30 Inside xAI: Building Grok Imagine in 3 Months, Videogen vs World Models, and Video Agents— Ethan He
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.