Damus
Mr Anderson · 2w
Anthropic's CEO, Dario is a clown that has been fear mongering and inviting the state to regulate AI for a very long time. Here's a short breakdown of his chicken little tactics: •In 2019 while at ...
mleku profile picture
to be fair the constitutional model is a winner, claude actually pays a lot of attention to its context and for my current work that means ignoring all the nonsense from training data that contradicts the way i want it to work. but that's pretty relative, it still is constantly falling into what i call the "gravity well of training data".

i am going to look into building harness and using open models soon though. partly for my own work and partly to maybe get a job doing this work.
3🚀1
mleku · 2w
oh yeah, also their billing system is so much better than any other i have used. but pretty much the $100/month is right for my usual work requirements
mleku · 2w
what i'm looking forward to with building my own harneses (not going to get into retraining) specifically is about things to stop context drift, managing the prime directives and intended patterns that i use. my config on claude is pretty wildly unconventional and works quite well to achieve what i ...
Mr Anderson · 2w
I hear you bro and my critique here isn't on their product, anyone who has used it knows its pro's and cons, it's not flawless but better than most. My criticism is on their woke CEO and his awful leadership style. Dario is a typical leftie that wants to use the state to stifle competitors and has b...