Qwen3.8 A95B

mentions 2 type Person feed RSS

// recent coverage 2 mentions

17:24

2026-09-09

gist.github.com

large-language-models

Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

A developer's v1.1 experiment reran reasoning-prefill tests using GPT-5.5 Pro as the teacher across 45 problems, finding that Qwen3.8 A95B's unigram source recall jumped from 33.92% to 54.50% (+20.58 …

14:24

2026-08-16

gist.github.com

artificial-intelligence

Show HN: Reasoning prefills on a few open models

A developer's independent analysis of reasoning prefills on open models finds that Kimi K3 shows a significant accuracy increase on Humanity's Last Exam questions when prefilled with Opus 4.8 reasonin…

// co-occurs with top 7 entities

Opus 4.8 2 DeepSeek V4 Flash 2 Inkling 2 Kimi K3 2 Humanity's Last Exam 1 Stolen Thoughts 1 GPT-5.5 Pro 1

// topics top 4 topics

large language models 2 ai research 2 artificial intelligence 1 machine learning 1