Oh! An open-source alternative of anxiety and hierarchy!
NiceThis 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.
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.
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.
Thank you, I am trying this in my Claude instance and will see where it goes
I just tried this with Qwen3:4b (Ollama) and AnythingLLM. It works extremely well with the exact prompt you provided. Fantastic work!
Awesome! Thanks for your kind words. I’d love a report on what you notice as you play with it.
I should have saved what the LLM said, with the exact questions you posed. It was certainly similar from the looks of things, given that I used, word for word, the system prompt and the questions I put in chat. I’ll probably do it again and maybe put that in the responses.
Cool read ദ്ദി ˉ͈̀꒳ˉ͈́ )✧
