Software 3.1? – AI Functions
blog.mikegchambers.com
Software 3.1? – AI Functions
1–10 of 61 posts
Re: Software 3.1? – AI Functions
#2AWS just shipped an experimental library through strands-labs, AI Functions, which execute LLM-generated code at runtime and return native Python objects. They use automated post-conditions to verify outputs continuously. Unlike generate-and-verify approaches, the AI-generated code runs directly in your application.
Re: Software 3.1? – AI Functions
#3This looks like Symbolica, except the great thing of what they are doing is that they are setting new ARC-AGI records.
Re: Software 3.1? – AI Functions
#4Obvisouly you have never built software. English is a terrible programming language, you cannot have ambiguity in defining your computation.
Re: Software 3.1? – AI Functions
#5> Now consider a different arrangement. The LLM generates code that actually runs inside your application – at call time, every time the function is invoked.
I'm sure there's a lot of effort put into this, god knows why, but I pray I never have to have this in a production environment im on.
Re: Software 3.1? – AI Functions
#6Could you do this with erlang’s term to binary functionality?
Re: Software 3.1? – AI Functions
#7This is a terrible idea
Re: Software 3.1? – AI Functions
#8People did this 3 or more years ago. It's funny, but no less dumb now than it was then.
Re: Software 3.1? – AI Functions
#9I can't even imagine how many joules would be used per function call!
As an experiment, it's kind of cool. I'm kind of at a loss to what useful software you'd build with it though. Surely once you've run the AI function once it would be much simpler to cache the resulting code than repeatedly re-generate it?
Can anyone think of any uses for this?
Re: Software 3.1? – AI Functions
#10There were people doing this sort of thing 2-3 years ago. What are they doing now?