
6 days
Amen. And LLMs have a bias for producing text. And the more questions I ask it, for example to solve more edge cases, it quickly escalates on the existing suggestion rather than find a new approach.

Amen. And LLMs have a bias for producing text. And the more questions I ask it, for example to solve more edge cases, it quickly escalates on the existing suggestion rather than find a new approach.
And it’s $2.18 from 1987 to 2026 you absolute towel warmer

Speaking as someone who does some work for Stallman, although he is right 99% of the time, that last 1% is a doozy

I feel seen. I’m trying to sort out how to socialise the idea that we should be working with a broader context in mind. Hard to break habits.
You can fix this on the google side