[Vegenoid]

> people interface with LLMs directly rather than software at all

What does this mean? An LLM is used via a software interface. I don’t understand how “take software out of the loop” makes any sense when we are using reprogrammable computers.

[FridgeSeal]

It’s just…the vibe of it man! It’s LLM’s! They’ll just…do things! And stuff…it’ll just happen!!! Don’t worry about the details!!!!

[ethbr1]

The strongman for it would be:

Our current computing paradigm is built on APIs stacked on APIs.

Those APIs exist to standardize communication between entities.

LLMs are pretty good at communicating between entities.

Why not replace APIs with some form of LLM?

The rebuttal would be around determinism and maintainability, but I don't think the strongman argument is weak enough to dismiss out of hand. Granted: these would likely be highly-tuned, more deterministic specialized LLMs.

[Vegenoid]

Maybe this is a failure of my imagination, but I still don’t understand how “replace an API with an LLM” makes sense. LLMs just generate text, the only way they have of interacting with software is by generating text that the software can parse - a.k.a. an API call.

Maybe I have some misconception here. I think seeing a program or system that is doing this “replace APIs with LLMs” thing would help me understand.

[Eisenstein]

I think it would more take the form of 'LLM makes a backend solution using deterministic code that it uses to solve the problem'. Since LLMs are already extremely good at code, then they could code the solution to the problem and use that internally to solve it. They would manage the information exchange and the operations, but the results would be from connected pieces of bespoke software.