No. Why the hell would I use Angular 1.x style directives in 2026? For the simple contact form and todo apps, why would I even use client side scripting? Go away.

You've been spamming this in a few threads.

A private business can 100% refuse service to you. Examples with regards to "delegation":

- If you come in using a form of non-cash payment that doesn't belong to you.

- If you're purchasing a car, and are filling out paperwork under someone else's name. FYI, you can buy cars on Amazon.com.

- If you attempt to pick-up a pre-order or an item earmarked for someone else.

...

Of course some businesses are more or less restrictive base on fraud chance, yada yada, but you get the idea. You're not being oppressed. Go shop elsewhere.

Apologies, I didn't mean to spam, haven't seen the other thread that picked up more votes and was really curious about where the line is.

I completely understand private businesses having a right to refuse a service without a cause. But as others pointed, the question is to what degree "delegation" is acceptable if I'm acting in a good faith?

I'm guessing the answer is "to a degree it doesn't impact our business".

I don't think any of your examples are analogous to the questions/point the GP was trying to make. Your questions seem to be centered around someone trying to trick or defraud a retailer; GP's is about simple, straightforward delegation.

But yes, agreed, businesses have the right to refuse service to anyone (outside of illegal discrimination).

We should fight it, though, when those refusals are backed by anti-consumer practices. It's pretty clear that Amazon doesn't like agent-mediated purchases because it allows the customer to bypass Amazon's ability to put sponsored products in front of you, and try to get you to buy related and add-on products along with what you actually want.

Sure, it is their right to do that, but as consumers I think we shouldn't be complacent and just take what the big shopping overlords feed us. Consolidation (and races to the bottom such as this) is making it harder and harder to find competing retailers and products when we want to vote with our wallets as to what kinds of shopping experiences are acceptable.

And the bottom line is that if Amazon realizes that they're losing sales because people want to use AI agents to buy things, and they're banning those agents, they'll change their tune. But that only works so long as there are alternatives with better practices, and, well... there aren't many.

> top of a regular API

What is the regular API? How do you express all the integrations needed in this API? Who provides the integrations? Answering these questions lead you back to something like an MCP, which is an API contract that can be as generic or as specific as needed. Wasting context window to understand and re-implement each integration is why MCPs exist.

All the security issues are orthogonal, and occur regardless if invoking this API occurs via code or natural language.

The security issues are probably orthogonal in the way most people install and use these MCPs, but the article mentions Cloudflare's "code-mode" running in v8 isolate sandboxes and calling rpc bindings that are pre-authed, no API keys or open slather internet access required, see: https://blog.cloudflare.com/code-mode/#running-code-in-a-san... This is at least interesting, possibly even novel.

"Wasting context window to understand and re-implement each integration is why MCPs exist" does seem to be exactly the point. Pointing the LLM at a swagger/openAPI spec and expecting it to write a good integration might work, but gets old after the first time. Swagger docs focus on what mostly, LLMs work better knowing why as well.

And,why not just use a locally installed cli rather than an MCP? You need to have one for a start, and use-cases (chained calls) are more valuable that atomic tool calls.

There is more behind the motivation for MCP and "tool calling" ability generally with LLMs. This motivation seems less and less relevant, but back when reasoning and chain-of-thought were newly being implemented, and people were more wary of yolo modes, the ability for an LLM harness to decide to call a tool and gather JIT context was a game changer. A dynamic RAG alternative. MCP might not be the optimal solution long term. For example, the way that claude has been trained to use the gh cli, and to work with git generally is much more helpful than either having to set up a git MCP or getting it to feel its way around git --help or man pages to, as you said "re-implement each integration" from scratch every time.

LLMs are able to use OpenAPI definitions to write code.

... maybe you don't get it?

_Telling the browser how you want the DOM manipulated_ isn't the expensive part. You can do this just fine with Javascript. The browser _actually redrawing after applying the DOM changes_ is the expensive part and won't be any cheaper if the signal originated from WASM.

It's winning by default because _there is nothing materially better_. React was _materially_ better than Ember, Angular, plain JQuery, etc. at the time.

Front-end engineers have no issues adopting new frameworks. See the common complaints about the speed front-end stacks change vs. say Spring MVC or Rails.

A more interesting examination is what is the impact of agentic AI tools being able to write better, more idiomatic code in React vs. Svelte because there's more of it. The human side is less of a barrier here.

And this is good or matters to customers because?

There’s no rational answer to this.

They want thin phones for the same reason they like fast cars. The same reason that ice cream tastes good.

Why do (some) people like jazz music?

Phones are the leading cause of RSI.

The Osborne 1 weighed ~25 pounds. I'm glad computer makers have put in the work to make computers faster and lighter over time.

Easier to drop in the toilet?

This analogy would make sense if the saw lacked a basic and obvious safety feature (billing limits) because Stanley profited immensely from cutting your finger off.

What seems like a basic feature to you is a hindrance to me. I don’t want to have to disable “safeguards” all over the place just because of loud and rare complaints.

It's as easy as having a single option:

> Do you want safeguards to be enabled by default, so you have to disable manually those you want to resign from?

OR

> Do you want safeguards to be disabled by default, so you have to enable manually those you want to be in place?

To then rebel against it and say "I lose seconds of my life reading this, I don't want to have to!" would be ridiculous.

Protect yourself how? Most cloud providers don't support any way to immediately abort spending if things get out of hand, and when running a public-facing service there are always variables you can't control.

Even if you rig up your own spending watchdog which polls the clouds billing APIs, you're still at the mercy of however long it takes for the cloud to reconcile your spending, which often takes hours or even days.

Yes, they do. You create resources and you delete resources and if you care about cost you creat alarms and tie them to scripts that automatically delete resources.

It’s basic stuff.

Those alarms can take hours to cut in, because AWS does not report costs in real time

It's true that they can but mostly they don't (particularly with "serverless" services).

> I ended up losing a finger

You forgot to mention Stanley Tools paid for the hospital bill.

No. Stanley Tools owns the hospital and would profit from the operation, but when you said you don't have the money they decided to let you go. Perhaps because legally they would have to anyway, or otherwise they would suffer various legal and reputational consequences.

This is a good analogy. When you use a tool you are responsible for what it does.

I'm a safety inspector. Of course this is much more nuanced than this. One crucial aspect of a tool safety is proper documentation. It's also important who the tool is targeted for. There are different safety standards based on user's competence. Some "tools" will be toys for children, some will be for disabled people including people with intellectual disabilities, some will be for general populace, and only some for trained experts.

If a tool is designed for experts, but you as the manufacturer or distributor know the tool is used by general populace, you know it's being misused every now and then, you know it harms the user AND YOU KNOW YOU BENEFIT FROM THIS HARM, AND YOU COULD EASILY AVOID IT - that sounds like something you could go to jail for.

I think if Amazon was a Polish company, it would be forced by UOKiK (Office of Competition and Consumer Protection) to send money to every client harmed this way. I actually got ~$150 this way once. I know in USA the law is much less protective, it surprises me Americans aren't much more careful as a result when it comes to e.g. reading the terms of service.

> You're getting a billion applicants because people are desperate and there are tons of CS grads, not because you're the greatest company on earth

How does this change the point? They would still like the best candidate out of that pool, not any warm body, since they have limited positions.

What is your approach to hiring and evaluating talent knowing the large number of applicants and how easy it is to _talk about software development_ vs. _actually developing software_, and how expensive and difficult it is to deal with a bad hire, even in America.

> The same reason I’d be uninterested in reading that the Daily Mail wants to investigate something but interested if NYT wanted to.

Has Gamer Nexus produced shoddy work in the past? The comparison feels lazy.

I’m more than happy to read a short sellers investigative piece, for example. You don’t need to be journalists to produce good work backed by facts.

They are just a linus tech tips bootlicker who thinks that there exists some mystical high standard journalism. You could find plenty of shoddy work from sites they consider good.

Major monopolies tend to have the most resources, particularly excess resources that are available to spend on things like research.

That’s not suprising at all, though. It doesn’t imply that monopolies are a net benefit for society.