Videos
3 total
| Thumb | Title | Channel | Status | Published |
|---|---|---|---|---|
|
The Inference Frontier: from 100 to 10,000 tokens per second — Sean Lie, Cerebras CTO
Cerebras CS4 runs GPT-4 at over 4,400 tokens per second, and the upcoming CS5 targets 10,000 TPS for medium models... |
Latent Space | summarized | 2026-09-02 17:05 |
|
Cancel your subscriptions, Ox-Alpha is here! (GLM 5.3 Flash)
GLM 5.3 Flash, revealed as the mystery 'Ox-Alpha' model, delivers near-frontier intelligence at roughly 2–3% of the... |
Matthew Berman | summarized | 2026-08-29 22:56 |
|
Everyone Got Xiaomi's AI Cube Wrong (4 Errors, One Spec List)
Xiaomi's X-Ring O100 chip achieves 1.22 TB/s memory bandwidth by using wafer-on-wafer hybrid bonding at a 1.4 micron... |
Cloud Codes | summarized | 2026-08-26 09:00 |
Frontier News · by Hyperjump Technology