November 8, 2026
Tess-4.5: bug fixes took 38% less time than Qwen3.8 in a private test
In a Nov 8 test, Tess-4.5 fixed bugs in 8 minutes versus 13 for the baseline Qwen3.8 27B, with a comparable number of fixes.
Loading the page.
who it's about
Layer →
about the same entities
Insight
See an LLM at work from the inside: one Qwen3.8-27B prompt traced through 64 layers in 3DOctober 26
Release
DeepSeek and Tencent open their own search for AI: site authority decides what gets into the answerOctober 23
Insight
--moe-cache-mib in llama.cpp: GPU expert cache speeds up MoE model 2.2x on RTX 5090October 21
Insight
Vertical AI agents differ from general-purpose ones in three layers: context, harness, and modelOctober 20
All news
One email a week - only what changes how you work. Subscribe