News for hackers. Stuff that matters.
Re:Humanising LLM Outputs Is Dumb by Havoc on Monday August 10, 2026 @01:28PM (#49246901)
> The problem is that these instructions are not applied after the model has finished doing the work

Seems like something fixable with a simple two step process. Ask it the thing. Then ask it to summarise the answer in simpler terms. More tokens and time aside that would check both boxes

Re:Humanising LLM Outputs Is Dumb by kuberwastaken on Monday August 10, 2026 @01:48PM (#49247173)
pretty much what I do, better yet ask it to boil it down in visuals in a simple webpage if it's a very large project
Re:Humanising LLM Outputs Is Dumb by StyloBill on Monday August 10, 2026 @01:38PM (#49247025)
Should be a harness feature actually.