[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![predict_addict Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::1464965267830804482.png) Valeriy M., PhD, MBA, CQF [@predict_addict](/creator/twitter/predict_addict) on x 34.1K followers
Created: 2025-07-21 09:48:13 UTC

There have been “scalable” approximations proposed since the Stone Age (Sparse GPs, inducing points, variational fluff), but they all compromise accuracy and rarely work in the wild. Deep learning eats GPs for breakfast in both performance and runtime.


XXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1947232134038471118/c:line.svg)

**Related Topics**
[gps](/topic/gps)

[Post Link](https://x.com/predict_addict/status/1947232134038471118)