aivibe-codingBACKGROUND
Qwen 3.8 27B in its default reasoning settings in LM Studio of "extra high" is a
BACKGROUND
1 SIGNALFIRST DETECTED 15 August 2026
Narrative synthesis pending — 1 signal collected.
How the story developed
15 Aug
Qwen 3.8 27B in its default reasoning settings in LM Studio of "extra high" is a chronic over-thinker and I kind of love it
OPINION · WHAT · Simon Willison
Other feeds and industry voices
16 Apr
Qwen 3.6: worse adherence?
<!-- SC_OFF --><div class="md"><p>Just swapped Qwen 3.5 for the 3.6 variant (FP8, RTX 6000 Pro) using the same recommended generation settings. My stack is vLLM (v0.19.0) + Open
OPINION · WHERE · LocalLLaMAOPEN STORY
17 Aug
Qwen 3.8 thinks like I do when choosing what hardware to buy
<!-- SC_OFF --><div class="md"><p>I've been using Qwen 3.8 for the last few days and I have to agree that it does looooove to think. But reading through the logs it suddenly
OPINION · WHEN · LocalLLaMAOPEN STORY
15 Apr
Been trying to get Qwen 3.5 to stop reasoning using old methods like /no_think, it didn't work, but it said something like "too late" in its reasoning
<!-- SC_OFF --><div class="md"><blockquote> <p>Wait, I need to be careful about the "no_think" tag in the system prompt. The system prompt says <code>/no_think</code>.
OPINION · WHO · LocalLLaMAOPEN STORY
Sources
Simon Willison
NewsHive monitors these sources continuously. All signal titles above link to the original reporting.
Intelligence by NewsHive. Need help navigating what this means for your business? Contact GeekyBee →