Test: Style-Adjusting Skills Affect Model Chain of Thought
eliebakouch · x · 2026-08-24
An experiment reveals that using a skill to adjust a model's output style also impacts its Chain of Thought. Instructing the model not to apply the style during reasoning did not alter the outcome. Additionally, the author notes that DeepSeek V4 Pro almost never uses em dashes.
Related event: Style Skills Quietly Rewrite Model Chain-of-Thought(2 posts)→
More from Models
- Anthropic Addresses Opus Verbosity with Config Command — kimmonismus · 2026-08-24
- Uncensored Qwen3.8-27B Model Trends on Hugging Face — orcarouter · 2026-08-24
- SemiAnalysis: $200/mo AI plans can yield up to $8K-$14K in tokens — scaling01 · 2026-08-24
- Voice AI Startup Modulate Takes #1 Spot on Hugging Face's Transcription Benchmark — jonathan_wilke · 2026-08-24
- Ox Alpha questioned as overhyped; early tests show non-frontier performance — peterwildeford · 2026-08-24
- Rumor: Anthropic testing Haiku 5 and Sonnet 5.1 instead of Fable 5.1 — ChrisGPT · 2026-08-24