Presumably you do a lot of back-and-forth with AI, and as many other commenters have pointed out, this seems to have made you more credulous and less informed.
The US healthcare system is not a market system nor did it occur naturally. Do you have any conflicts of interest that could cause you to have an emotional need to misunderstand basic information about it?
I can deeply, deeply relate. X and Bluesky are both going nuts with ai and ai scams, but _both_ of them banned an advertising account because we were... using a bot to automate behavior because their APIs are only a subset of functionality.
Their vision is a world where they use all the automation regardless of safety or law, and we have to jump through extra hoops and engage in manual processes with AI that literally doesn't have the tool access to do what we need and will not contact a human.
I would spend less time with theory and more time with practice to understand what people are getting at. MCP and CLI could, in theory, be the same. But in practice as it stands today, they are not.
> MCP is just a way to write this in a structured way,
Nope! You are not understanding or are actively ignoring the difference which has been explained by 20+ comments just here. It's not a controversial claim, it's a mutually agreed upon matter of fact by the relevant community of users.
The claim you're making right now is believed to be false, and if you know something everyone else doesn't, then you should create an example repo that shows the playwright CLI and playwright MCP add the same number of tokens to context and that both are equally configurable in this respect.
If you can get that right where so many others have failed, that would be a a really big contribution. And if you can't, then you'll understand something first-hand that you weren't able to get while you were thinking about theoretically.
> then you should create an example repo that shows the playwright CLI and playwright MCP add the same number of tokens to context and that both are equally configurable in this respect
That's just implementation detail of how your agent harness decides to use MCP. CLI and MCP are on different abstraction layers. You can have your MCP available through CLI if you wish so.
Please, please, please actually do this yourself or read any of the top comments. You are still missing the point, which you will understand if you actually do this and then look at the logs.
Fair enough, I’ll give it a try when I’ll have time for it.
I recognize that MCP as typically used would eat a good chunk of context - shoving all those API specs is wasteful for sure. The solution to this, I believe, is either RAG or single-tool (Context7-like), where relevant APIs are only provided on demand from models’ intermediate requests.
Caveat is model may need training to use that efficiently (or even at all, esp. smaller models are either very shy or crazy with tool use), and I don’t want to spend time fine tuning it. Could be that’s where the reality may prove me wrong.
But a token is a token. There is not a lot of difference between Playwright (or any other tool) use documentation wrapped in JSON with some logical separations, or provided as a long plain text blob (ultimately most likely also wrapped in JSON). So if the model doesn’t know how to use some tool innately (it may, for Playwright), and if it needs to use all tool functionality, I’m sure a CLI wouldn’t fare any better that MCP. But if the model knows the tool or needs just a small bit of its capabilities - naive MCP is going to be a bad idea.
Just like a human. If all I need is some simple thingy, I probably don’t need a whole textbook upfront, just a select excerpt. As far as I understand MCP, supplying full textbook in the system prompt is not MCPs innate design fault, it’s merely a simplest implementation approach.
I'm rooting for you, to be clear! It sounds like your approach is more sophisticated than the average, and this is a pain point that is starting to get a lot of attention.
The majority of US support for Taiwan and it's current situation is owed entirely to supporting a military junta from the mainland that massacred the local Taiwainese who objected to it and suppressed civil society.
Are you saying you would've been neutral on an invasion of Taiwan before 1985 or so, since it wasn't a democracy?
I applaud your consistency and I await your categorical opposition to the United States and Israel.
Or is there some nuance and you feel, in order to remain consistent, that it would be permissible in principle for China to bomb Taiwan and execute their head of state so long as they kept it to an air war and relied on their local agents on the ground?
I would also like to know if these are dual citizens or not. I think it would be newsworthy if hundreds of US passport holders who do not have chinese passports also were being held in China and not charged with any crime and unable to access consular services.
Sensationalizing claims then qualifying them later is inherently dishonest.
> A two sentence comment requesting one piece of information that is highly likely to be collated with the original information for any reputable source
You would describe that as "relentless, harassing, and tangental?" rather than say "I can see how that would be a relevant question, I'm not sure."
I hope your mental health improves in the future, it's unfortunately not possible to assume good faith on your part when you jump to thought terminating cliches.
I don't doubt you, but what if someone's else's wife felt differently. Would that counteract your wife? Or is your wife special in an objective sense and her intuitions about hypotheticals are more valid than anyone else's?
Your wife feels a certain way and wanted to avoid a certain hypothetical. But since it didn't happen, we have no way of knowing how relevant these feelings are.
How can we address blacklisting and covid response if you are insisting that any comparison isn't relevant and that we should evaluate it with no baseline?
I don't recall insisting that no comparison could be relevant. If you have any particular comparison to offer, you should do that, else your criticism is vapor.
What are you talking about? Why are you using imprecise language like "popped the camera open?"
You've run into a site you view on chrome/firefox/safari accessing your camera without granting access a few times now?
Can you give us an example of a site that does this so we can reproduce? Or could you retract your statement and clarify that you did grant camera permissions for that site previously?
Otherwise, you're saying very casually there's a huge bug and security issue that no one else has detected but you personally have seem multiple times.
I've run into people on the internet misremembering things or not understanding how the browser works more times than I've run into browsers allowing access to system devices like the camera without a permission prompt.
> Or could you retract your statement and clarify that you did grant camera permissions for that site previously?
I never said anything about granting permissions. I can respond to your other points, in turn, but first I would like you to confirm that I am who you think you are responding to :) I am not OP.
In case you don't think I'm OP, then, well I was being imprecise. Yes, it requires browser/app/manifest permissions. Your paranoid and aggressive tone implies you're not giving me any benefit of the doubt, as I speak informally in a casual web forum discussion about understanding what happened.
Sorry, I think of HN as a technical forum where people prize precision.
I think that when you informally bolster lies of omission with your own imprecise language agreeing with it, that harms the quality of discussion and creates pointless confusion. I think you get less benefit of the doubt if you do that routinely. By your own admission you do that routinely since you use this as a place to speak informally in a casual web discussion where you are often imprecise or lie by omission.
Actually, I didn't bolster a lie by omission. I provided context as to what their experience might be based on my own.
It is entirely possible that they aren't lying. That is your assertion that you are making as if it's fact. I think it's more likely that they are unaware of what is happening. You didn't have all of the information, and you are making assumptions that are very likely incorrect.
Furthermore, it is a given that user consent is asked for camera access in most situations. If this is a concept that you need explained to you in every situation, then you may need to review your knowledge or competency.
Which is to say, if you need this explained, you should probably speak less and listen more :)
Anyways, I think this conversation is over. Your unnecessarily aggressive and hostile tone is unwarranted and I no longer wish to talk with you. Feel free to have the last word if you wish. .
You're stringing together a bunch of weasel words that are not a proof or a plausible suggestion of a proof.
"Suggests is more ambiguous" and "undermines the framing" are bare assertions you want to be true based entirely on your mental model that has several shaky unsupported axioms.
I would guess that anyone who describes that problem as "underspecified" has some kind of serious brain injury or is below A2 english proficiency and should be excluded from the dataset, but I would not assert that definitively as self-evident.
Tell me you've never done any farming in your life without telling me you've never done any farming in your life. The difference between male and female animals matters, a lot, to farmers (or ranchers). There's a reason the English language has the words cow and bull, sow and boar, ewe and ram, rooster and hen, nanny and billy, mare and stallion, and many more (and has had those words for centuries). And that reason is precisely because of how mammal (and avian) reproduction works. A cow can't do a bull's job, nor vice-versa, if you want to have calves next year, and grow the size of your herd (or sell the extra animals for income). And so, centuries ago, English-speaking farmers who didn't want to spend the extra syllables on words like "male cattle" and "female cattle" came up with handy, short words (one-syllable words for most species, though not goats and horses) to express those distinctions. Because as I mentioned, they matter a lot when you're raising animals.
You might believe there is intrinsic sexual dimorphism among mammals and birds. You might even have overwhelming experimental and scientific evidence that proves it. But ask yourself: is it worth losing your job over?
