psyphy

Some highlights:

(1) Works with any OpenAI-compatible endpoint.

(2) Supports all <textarea /> customizations

(3) Customizable `purpose` prompt.

(4) Provide arbitrary context to inform autocompletions using `useMakeCopilotReadable`

> The problem with amateur philosophers like you an me is that we want to talk more than listen.

that's some healthy self-awareness :) (for someone jumping to conclusions without bothering to read the introduction to the linked paper, and without knowledge of who read it and what they thought of it- which may surprise you).

I truly have no animosity towards you, I am even glad you engaged. But meta-social discussions with "amateur philosophers" is indeed not what I am looking for. Farewell :-)

Heh, one thing I can tell you- it is NOT easy to define the hard problem in a way that allows a neat theory. It took me a couple of physics degrees + years of work, and really, a lifetime of obsession. And I am not done yet.

But you are right about the social problem- consciousness studies is terribly fragmented, and everyone agrees it is mostly full of nonsense (only disagreeing about which parts are nonsense).

Motivating serious examination by domain experts is extremely difficult - completely independently of the coherency of your ideas, and to some extent even of your pedigree.

You can try to solve this social problem by personally climbing the status hierarchy. Or by doing your best to distill a convincing introduction to a few minutes of reading.

This is an attempt at the latter.

The Hard Problem of consciousness is a stop-gap term for a deeper, more precise, and more solvable(!) problem buried within; a problem that a physicist would call the kinematical problem of consciousness.

—

This short article will characterize the kinematical tension at the heart of the Hard Problem: a mismatch between our model of the universe and 2 specific qualities we implicitly ascribe to consciousness (qualities which may be called ‘classical indescribability’ & ‘non-emergent integration’.) Then, having reframed the Hard Problem as a precise & explicit problem of kinematics (physics), we’ll go on to motivate, outline, and reference an experimentally falsifiable resolution to the problem of consciousness.

Kinematics is all you need.

I just published CopilotKit, which lets you implement this exact functionality for any web app via react hooks.

`useMakeCopilotActionable` = you pass the type of the input, and an arbitrary typescript function implementation.

https://github.com/RecursivelyAI/CopilotKit

Feedback welcome