News for hackers. Stuff that matters.
Re:ai;dr by AnimalMuppet on Thursday February 12, 2026 @01:09PM (#46992605)
Well, LLMs can be either side of that. They can also be used to turn something verbose into a series of bullet points.

I agree that reading an LLM-produced essay is a waste of time and (human) attention. But in the case of overly-verbose human writing, it's the human that's wasting my time[1], and the LLM is gzip'ing the spew.

[1] Looking at you, New Yorker magazine.

Re:ai;dr by steveBK123 on Thursday February 12, 2026 @01:13PM (#46992659)
Right we are headed towards LLM generated slop summarized by another LLM. Wire format is expanded slop.
Re:ai;dr by account42 on Friday February 13, 2026 @05:13AM (#47001057)
> I agree that reading an LLM-produced essay is a waste of time and (human) attention. But in the case of overly-verbose human writing, it's the human that's wasting my time[1], and the LLM is gzip'ing the spew.

gzip is lossless, LLM summaries are not.

Re:ai;dr by jfengel on Friday February 13, 2026 @02:55PM (#47006984)
We can run each LLM-produced essay through an LLM to reduce it to bullet points.

We can then run it through another LLM to reduce it to a single bullet point.

Then we can run it through a final filter, which reduces it to "ai;dr".