Ideas & society2026 · shared on Hacker News
Google's extreme AI compression paper was on arXiv since April 2025
Explore Google's extreme AI compression paper was on arXiv since April 2025, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Ymeetpateltech ·
Mistral Medium 3.5
71 points26 comments
YLucidLynx ·
Hold on to Your Hardware
34 points12 comments
YEGreg ·
KV Cache Compression 900000x Beyond TurboQuant and Per-Vector Shannon Limit
31 points5 comments
Yadlrocha ·
What if AI doesn't need more RAM but better math?
10 points1 comments
Yomer_k ·
The RAM shortage could last years
6 points0 comments
Yray__ ·
TurboQuant: Redefining AI efficiency with extreme compression
2 points0 comments
Ygeoffbp ·
Google's TurboQuant AI-compression algorithm can reduce LLM memory usage by 6x
2 points0 comments
Yjustsomeguy1996 ·
Show HN: TurboQuant for vector search – 2-4 bit compression
2 points1 comments
Yfadijob ·
Google's extreme AI compression paper was on arXiv since April 2025
1 points0 comments