Discussion

JavaScript is not available.

scuff3d: The linked tweet leads to another tweet which leads to an article that doesn't say anything about OpenAI. It's talking about a new compression algorithm from Google potentially making memory usage 6x more efficient for LLM workloads.

supermdguy: Yeah that confused me, but the compression paper also doesn’t make a ton of sense since I doubt Google would have released it if it was actually such a competitive advantage compared to what other labs are doing. So I wonder what’s actually causing the price decrease.