Show notes
The single biggest bottleneck for Large Language Models isn't intelligence—it's cost. The quadratic scaling of self-attention makes processing truly long documents prohibitively expensive, a fundamental barrier that has stalled progress. But what if the solution wasn't more compute, but a radically simpler, more elegant idea?
In this episode, we dissect a groundbreaking paper from DeepSeek-AI that presents a counterintuitive yet insanely great solution: Contexts Optical Compression. We explore the astonishing feasibility of converting thousands of text tokens into a handful of vision…
Website: podcasters.spotify.com
