Humanising LLM Outputs Is Dumb
- ID
- 12998
- Status
- summarized
- Published
- 10 Aug 2026, 9:35 PM
- Fetched
- 12 Aug 2026, 4:55 AM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://kuber.studio/blog/Reflections/Humanising-LLM-Outputs-is-Actually-Dumb
- Source URL
- https://hnrss.org/best
Summary
- Score
- 7.0
- Created
- 12 Aug 2026, 6:03 AM
- Tags
- Audience
- developersvibe_codersai_agent_users
What happened
Kuber Mehta argues against using prompt instructions like 'I have ADHD' or 'use ASD-STE100 Simplified English' to 'humanise' or constrain LLM outputs. The core issue is that these instructions become part of the model's reasoning process rather than a post-processing filter, which degrades the actual work.
Why it matters
Builders should stop injecting persona or stylistic constraints directly into the main system prompt if it affects reasoning. Instead, separate the generation of the core content from the formatting or stylistic translation to avoid degrading the model's primary task performance.
Discussion angle
Should we use a two-step pipeline (generate content, then rewrite for style) instead of bloating system prompts with persona constraints?