A slightly different activation strength makes Qwen3-8B write a different song
sterlingcrispin · x · 2026-09-29
sterlingcrispin shares an alternate song Qwen3-8B wrote under slightly different activation strengths, showing how small internal activation changes noticeably alter generation.
More from Models
- Anthropic launches Claude Sonnet 5.5: 56 on AA Index, just 2 points behind Opus 5.5 — jarrodwatts · 2026-09-29
- PrivacyBench v2 launches: micro1's flow-transform 1.0 leads at 95.84%, 9.64 points ahead — Exp_Mark · 2026-09-29
- Grok 4.7 xHigh Tops Artificial Analysis Cyber Index for Enterprise Cyber Defense — XFreeze · 2026-09-29
- Dev Re-Verified Benchmarks Repeatedly: New Model Complements Opus 5.5 — giansegato · 2026-09-29
- Anthropic exec on Sonnet 5.5's design skills, teases Haiku 5.5 within weeks — mikeyk · 2026-09-29
- Leak claims OpenAI GPT-6 sol brutally outclassed by Claude Sonnet 5.5 — ns123abc · 2026-09-29