Videos
2 total
| Thumb | Title | Channel | Status | Published |
|---|---|---|---|---|
|
Which is The Best Qwen3.8-27B?
Multiple fine-tuned versions of Qwen 3.8-27B now claim to reduce thinking tokens by 37-58% while maintaining... |
Sam Witteveen | summarized | 2026-10-04 16:20 |
|
Random Attention: They Deleted AI Memory at Random (And It Got 43% Faster)
Random Attention, a technique that randomly deletes entries from the KV cache, achieves 32-43% higher throughput... |
Cloud Codes | summarized | 2026-09-08 09:23 |
Frontier News · by Hyperjump Technology