FRAMEWIREIndonesiaUpdated Sep 24Live wire
0:00 / 0:00

Ok here's my voxel pagoda "Thai Island Paradise" - Qwen 3.8 Flash Next using the EXL3 engine (credit…

Ok here's my voxel pagoda "Thai Island Paradise" - Qwen 3.8 Flash Next using the EXL3 engine (credit ViC305 ) which I patched for Hermes (patch/recipe attached). 142,000 voxels, 61k decode tokens - for all you pagoda lovers: wikiwayne Tech2Wild WescheNex1q JoelDeTeves

James AitaSep 247
0:00 / 0:00

This is so freaking sick!

I love botting. i’m going through and improving the gym and world model. qwen 3.8 27b on my rtx5090 with jev for fighting. (thinking turn pauses removed)

ausbOSS - e/accSep 241
0:00 / 0:00

Looking forward to it!

Current OpenClaw doing a 7sec run with Sol as primary, Luna as light and Jev (or Qwen 3.8 Flash Next just 2sec slower) searching for a flight in a VM. We implemented decision models with the current OpenClaw version on OODA AI and a bundled VM with

OODA AISep 23
0:00 / 0:00

I just ran the largest speed and capacity test for almost every entry AI subscription.

How did Opus 5.5, GPT 6 Sol and Grok 4.7 etc. stack up? Let's find out! Every sub was tested in their own sandbox (asciidotdev) on the same exact 8 tasks (w/ 30 min cap per task). Here's a

Latent LocalSep 2334