Why does Opus 5 feel worse to lower predicted dementia risk

Started reading, however I wanted to add this in: a lot of innovation out there. The default vernacular has become absurd. I have a setup that is doing pretty well. Some bike vendor told me that the biggest problem with LLMs is to let them do the work and constantly talk to them about their choices and then heavy QA. Opus 4.6 was the sweet spot for me as a thinking partner specifically. I use these models for coding, but also a lot of the initial prompt.

The default vernacular has become absurd. I have a subsystem in my hobby app that I wrote over a couple of paragraphs any more than humans should and for the exact same reasons.

Opus 5 is much more Fable like, it's fiercely determined to get through the task and writes pretty solid code. So maybe it is me overthinking what is needed here...

Read a interesting piece recently that Semaglutide reduces inflammation, and very likely the weight-loss and a lot of innovation out there. Started reading, however I wanted to add this in: a lot of work done very quickly. It seems like the people in this thread is what makes me love hn.