[no_wizard]

Question three is what hits the nail on the head about how this “AI revolution” isn’t as robust as often claimed.

If it was truly intelligent it could reason about things like API specifications without any precursors or shared structure, but it can’t.

Are LLMs powerful? Yes. Is current “AI” simply a re-brand of machine learning? IMO, also yes

[vineyardmike]

> If it was truly intelligent it could reason about things like API specifications without any precursors or shared structure, but it can’t

I can reason about any API or specification. But when I'm trying to get a different, compound, and higher-level task done, its quite a bit faster and less distracting if I can rely on someone else to have already distilled what I need (into a library, cheat-sheet, tutorial, etc).

Similarly, I've seen LLMs do things like generate clients and scripts for interacting with APIs. But its a lot easier to just hand them one ready to go.

[no_wizard]

It doesn’t negate my point; the technology can’t self reason any API specification, and if it could this wouldn’t be needed because while humans benefit from this simplification why would a machine that can think 10000x faster than a human can?

[james_marks]

My impression, and perhaps this is wildly off, is that MCP could be useful to whitelist safe usage of tools by LLMs.

I say this out loud so someone can correct me if I’m mistaken!

[immibis]

Then it's a useless concept, because people who use LLMs don't want to be bounded by a whitelist.

[james_marks]

Strong disagree. I want absolutely control over what tools my agent can access on my computer.

[immibis]

Do you want your tech landlord to have absolute control over what tools your agent can use on your computer?

[james_marks]

As I understand it, I maintain the whitelist, not the tech overlord.

That’s sort of the point of MCP, as near as I can tell.

[zombiwoof]

Exactly Any junior developer can reason about API and integrate

But LLm will replace them?