Humanising LLM Outputs Is Dumb
The author argues that forcing LLMs to adopt human-like communication styles, such as simplified technical English, degrades their utility. They contend that raw, dense output is more valuable for AI-to-AI communication and that humanization often masks critical failure states.
Why it matters
As AI agents become more prevalent, the debate over whether they should mimic human prose or provide raw data is central to the future of AI-driven workflows.
The largest tell for me to tell where culture and sentiment is shifting for AI tools is usually X, viral GitHub repositories and Hacker News.
One of these tells I’ve been seeing a lot lately is skills like I have ADHD and Agents.md instructions such as giving outputs in only ASD-STE100 Simplified Technical English .
I understand the appeal, none of us really like the verboseness and specific quirks of LLM outputs, but I really think fixing that by humanising the model is the wrong abstraction.
The problem is that these instructions are not applied after the model has finished doing the work, it becomes part of the same work - If you tell an agent to use short sentences, avoid jargon, never overwhelm you and only include the most important details, you are asking it to continuously compress its output into a lower-bandwidth format.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in