1
What if AI doesn't need more RAM but better math?
How TurboQuant compresses the KV cache without losing accuracy, and what that could mean for memory stocks
Alfonso de la Rocha
My personal public journal. Reflections on cutting-edge systems, career pivots, and the mindset of an engineer in the age of AI. Click to read @adlrocha Beyond The Code, a Substack publication with thousands of subscribers.
- Popular posts
- 10
- Total points
- 1,831
- HN comments
- 1,113
- Rank
- #935 personal
Visit adlrocha.substack.com → RSS feedOn Hacker News Feb 2020 – Apr 2026
Software Engineering 6AI & Machine Learning 3Web & Frontend 2Math & Algorithms 2Tech Industry & Business 2Society, Policy & Culture 1
2
Finite State Machines
To infinity and beyond!