I have been speaking English for 20 years but it's my second language. I don't think the semantics of "up" matters when I try to understand phrasal verbs like "turn up". I don't see anything about "up" (as in a direction) in "turn up" or "show up" when it means "to appear" or "to be discovered"... where is the semantic connection?? I think native English speakers just think "up" intrinsically relates to "appear" or "be found" but there's no such connection in other languages I know of.

Similarly with things like "fed up" (as in 'tired of'). Where is the "upness" here?

If you haven't tried Zig since 0.16.0 was released, I highly recommend having a look. The release notes for this release were huge!!

https://ziglang.org/download/0.16.0/release-notes.html

With just an API, the agent needs to "read your API docs" to know how to call it (that can be an OpenAPI spec or even just text).

With MCP, the agent sees a bunch of tools it can call, and they've been trained to call tools so they nail it.

One more very important factor is authorization, which no one seems to mention in these discussions. CLIs were made for humans and use primitive mechanisms for authorization: either an API key you hardcode in your environment, or they literally run a background HTTP Server to get a callback OAuth call to receive a token from a browser authentication flow. Incredible that people are happy with that, appparently. With the MCP Authorization spec, you solve authorization across multiple MCP servers in the same standardized way, the LLM client you use just need to know the protocol, not how to login for every single MCP server.

Very importantly, if the MCP client does the authorization, the MCP provider has auditability: is this a call from a human or from a LLM? That's important in Enterprise! People think it's ok to let an LLM act on behalf of the human but that will eventually bite a lot of people. Did the LLM just try to hack the API while you were mindlessly clicking "yes" when it asked if you wanted to let it do something? Tough luck, there's no way to distinguish an LLM making a mistake from a human maliciously running some attack.

And as the post mentions, there's also more benefits like being able to "elicit" user input (not just request/response cycles) and the ability to have documentation and assets (skills also have this though).

But while the condition system can do many things you can also do with effects, they cannot do everything.

Here's another discussion on this: https://news.ycombinator.com/item?id=44078743

https://www.unison-lang.org/

https://flix.dev/

Well yeah, in the last 20 to 30 years in most countries the story has been the same. My parents bought a house in Brazil in the early 90's for 30k and we're now selling it for 400k. My relatives in Australia bought a house in Adelaide for 400k around 5 years ago. Prices exploded there and it's now around 700k. They got 300k dollars in a few years while actually earning less than that in salaries over the same period.

On the other hand, me, in Europe, managed to lose money on a house I bought 10 years ago because I overpaid (at the time it was really hard to buy as competition was huge) and after COVID, prices in my region fell 20% and never recovered... Also, I invested too much on a new building in the property which people in this country don't actually value a lot, so the investment did not pay off.

But before that I had made 60k on an apartment in just 2 years. So, while I know too well that the housing market can be unpredictable, I would continue to bet on it going up in most markets since the conditions which made prices increase have not changed.