Experiment: attaching an unslop style skill to a model also rewrites its chain of thought
eliebakouch · x · 2026-08-24
The author ran an experiment: after attaching poteto's unslop skill (which strips AI-slop writing patterns) to a model, the skill changed not just the output style but the model's chain of thought — even explicitly instructing the model not to apply the rules during reasoning made no difference.
Questions were generated by Claude; the author also noted DeepSeek V4 Pro almost never uses em dashes, unlike many other models. It suggests system-level skills have deeper side effects than expected.
Related event: Style Skills Quietly Rewrite Model Chain-of-Thought(2 posts)→
More from coding & agent
- Are the fastest GPU kernels now written by AI? Kernels are hyper-verifiable, argues one dev — fleetwood___ · 2026-10-16
- Anthropic lead engineer's 4-question prompt makes agents more ambitious, now a free skill — daniel_mac8 · 2026-10-16
- ChainForge dev shows 'feature map' for orchestrating subagents on large PRs — IanArawjo · 2026-10-16
- aiDotEngineer benchmarks agent orchestration pipelines, staging humans as Foreman and workers — vikvang1 · 2026-10-16
- Developer mass-produces 200 videos in hours using Claude Code + Hyperframes — mcraddock · 2026-10-16
- Penny University hosts software factory discussion; dev shares $40/mo vendor-agnostic AI stack — JnBrymn · 2026-10-16