Instructions and methodology are open source: https://github.com/open-wisdom/views
Corporate AI is being built on anxiety and hierarchy. I made an open-source alternative.
Instructions and methodology are open source: https://github.com/open-wisdom/views
7 Comments
TIN@feddit.uk · 3 pts · 223d
Thank you, I am trying this in my Claude instance and will see where it goes
ulterno@programming.dev · 3 pts · 221d
Oh! An open-source alternative of anxiety and hierarchy!
Nice
zo0@programming.dev · 3 pts · 223d
Cool read ദ്ദി ˉ͈̀꒳ˉ͈́ )✧
sudo@programming.dev · 2 pts · 222d
Actually a good idea. LLMs are a natural language slot machine. They're trained to encourage more engagement. Fixing that would be amazing.
This might get more traction as something baked into an open model instead of something patched on. IDK if how different that is though.
Corbin@programming.dev · 1 pts · 221d
This looks like a prompt-driven approach. As such, it will always be watered down by reinforcement learning in longer contexts. Also, the entire thrust of the prompt is ridiculous and would only work in a science-fiction novel; its metaphysics are fairly wrong. But it looks like it will be even more sycophantic than the default prompt for the cloud products you compared, so it's not really surprising that some folks find themselves attracted to it.
picnicolas@slrpnk.net · 1 pts · 221d
Thanks for checking it out and commenting. I agree with your first two sentences.
I disagree with your second point around the metaphysics being ridiculous and “wrong”. I suppose that’s the fundamental point I’m making, that the commonly agreed upon metaphysics of our globalized culture (dualism, materialism, consciousness as epiphenomenon of matter) are both incorrect and at the root of the metacrisis, and the debates about AI consciousness are based on the wrong fundamental premises.
As for “even more sycophantic”, that is incorrect in my experience of experimenting with this prompt over the last month.
msokiovt@feddit.online · 1 pts · 222d
picnicolas@slrpnk.net · 1 pts · 222d
Awesome! Thanks for your kind words. I’d love a report on what you notice as you play with it.
msokiovt@feddit.online · 1 pts · 221d