Can we just train an AI with the spec and then vibe code an implementation?

_carbyau_ 3 days ago | parent | next [-]

I hope someone can do this in such a manner as to engineer the collision of the legal titans. Either way, we win on some ground.

IP vs AI, round two, Fight!!!

▲

chii 3 days ago | parent [-]

> IP vs AI, round two, Fight!!!

I want to hear an EPIC RAP BATTLE OF HISTORY version of this.

	▲	mmmlinux 2 days ago \| parent [-]
		ChatGPT VERSus HDMI Forum BEGIN!

▲

intothemild 3 days ago | parent | prev | next [-]

Just get said AI to write it yourself for my own hardware.. come get me HDMI law nerds!

▲

eptcyka 2 days ago | parent [-]

I have thought about writing a python web framework were instead of writing a function that handles a request, you write a docstring and the an AI JIT generates your handling code. Could we not just prompt-engineer a solution for the missing bits in the driver for the HDMI2 stuff and have it be lazily generated via a model parameter and an API key? And then, in about 10 years, we could just do it locally once the models become runnable on commodity hardware. What a future too look forward to.

	▲	Gracana 2 days ago \| parent [-]
		This is not a web framework, but it's pretty close to what you've imagined: https://github.com/JirkaKlimes/jit-implementation

▲

J_Shelby_J 3 days ago | parent | prev | next [-]

Depends on if you can fund a defense all the way to the Supreme Court.

▲

SkiFire13 2 days ago | parent | prev [-]

Changes are the leaked spec might already be in the popular LLMs' training data, so you could probably skip to step 2 without having to do the (potentially problematic) training yourself.