121–130 of 139 posts
STE Misapplication issues and limited adoption https://en.wikipedia.org/wiki/Simplified_Technical_English#M...
“Writing correctly in STE is not an easy task as it requires a good command of the English language together with a good knowledge of the matter of the writing.”
This is simply what is required for good writing (in English) in any domain with or without STE.
https://youtu.be/uJblcC4lKYw This video benchmarks slop-style indicators with different skill/prompt solutions including the STE skill vs. George Orwell's six rules of writing prompt: Orwell came out on top overall. Additional bonus: it doesn't add much more tokens to input context. I have compared prose prompts with these rules and without and I am liking the results. 1. Never use a metaphor, simile, or other figure…
"now the honesty - those translation gains were real but small"
"and here is the honest part"
"same disease but with different symptom"
"so that brutal 3% number was a Claude quirk, not a law of nature"Earlier quoted context omitted.
New models (especially Opus 5, released just last week) produces unintelligible output, so people are trying to fix it.
No, it was a viral tweet from last week. They’ve been verbose since GPT-4o.
WTFs per prompt metric raised sharply for me :)
Agent skills work... sometimes - depends on the agent's mood really. I tried to solve this in a rather opposite way. https://github.com/computerreinvention/trie The documentation is updated and recording the intent behind all changes is enforced by a commit-gate. At the symbol level.
In contrast if you ask GPT 5.5/5.6 to speak directly/plainly, it will just straight up tell you the content "X is right, Y is wrong". Much preferable.
I like the idea, but not sold on the skill. But did lead to me finding https://vale.sh and its various available linters. Might give that a try.
How would one use Vale in LLM documentation?