FRAMEWIREIndonesiaUpdated Sep 12Live wire
0:00 / 0:00

Guys, imagine all this with one prompt via #deepseek and only one prompt

SaberSep 11
0:00 / 0:00

Astra-6 vs DeepSeek-v4.1 cloud vs local.

Same water prompt. Left → right: • Astra: “Worked for 30s” in ChatGPT • DeepSeek V4.1 Cloud: 103s, 28.5K completion tokens • DeepSeek V4.1 Local: 4× DGX Spark, 25m to HTML through Hermes 512×512 mesh. Click-to-ripple. Interacting

WëscheSep 1158
0:00 / 0:00

OKAY - took a long time but finally got some decent results with Deepseek v4.1 flash and 3D generation!

This is... well, not as straightforward than with GTP6 Astra 😅 But absolutely UNBEATABLE unit economics. Courtyard model took 34min to create, for a total of... $0.2 ! 🔥

Timothée Le BorgneSep 113
0:00 / 0:00

Kimi K2, GLM-5 and DeepSeek-V4 all trained with a Newton-Schulz-orthogonalized optimizer that Moonshot…

Kimi K2, GLM-5 and DeepSeek-V4 all trained with a Newton-Schulz-orthogonalized optimizer that Moonshot AI measured at roughly 2x AdamW's compute efficiency.

Temperature2.comSep 11