News for hackers. Stuff that matters.
Re:AI, Tools and Transformation by beecasthurlbow on Sunday September 06, 2026 @10:22AM (#49586799)
> I expect the gruesome writing style of LLMs to be fixed relatively soon, seeing how it can already be prevented with just a few lines of stylistic instructions

What instructions do you use to prevent the gruesome writing style? I have… not found this to be the case.

Re:AI, Tools and Transformation by jaynetics on Sunday September 06, 2026 @12:53PM (#49588375)
Currently I append the snippet below to prompts where I care about the resulting text. Just putting it in the context up front isn't as effective, and I assume if the overall prompt is large, or the context window is full, it will also be less effective.

> Use plain, clear, everyday language with a linear deductive flow; avoid hyperbole, juxtapositions, metaphors, analogies, punchlines.

Re:AI, Tools and Transformation by beecasthurlbow on Monday September 07, 2026 @02:32AM (#49594649)
I’ll try it thanks! I just got good mileage out of “don’t use ‘X, never Y’ format” on a document too, but I think linear deductive flow Covers it