This is one of the few places I think it's obvious why MCP provides value - an OpenAPI document is static and does no lifting for the LLM, forcing the LLM to handle all of the call construction and correctness on its own. MCP servers reduce LLM load by providing abstractions over concepts, with basically the same benefits we get by not having to write assembly by hand.
In a literal sense it's easier, safer, faster, etc for an LLM to remember "use server Foo to do X" than "I read a document that talks about calling api z with token q to get data b, and I can combine three or four api calls using this http library to...."
Like, really. If I open ms paint and just do some low effort scrawl, I have copyright on that. Level of effort has not ever decided if something is copyrightable or not.
For derivative works, there is real effort required to de distinct from the original. Maybe that's a more interesting discussion... Is low effort use of an AI insufficient to prevent the copyright from reverting to the original authors it was trained on?
No, the exact opposite. This says that if the AI that a bank is paying for locks your bank account in error because your name sounds <ethnicity with a lot of locked bank accounts>, it's the banks problem to fix, not yours to just live with (entirely. You still likely have a problem).
> I don't see 5-10x more useful features in the software I use, or 5-10x more software that's useful to me, or that the software I'm using is suddenly working 5-10x better, etc.
This has bad assumptions about what higher productivity looks like.
Other alternatives include:
1. Companies require fewer engineers, so there are layoffs. Software products are cheaper than before because the cost to build and maintain them is reduced.
2. Companies require fewer engineers so they lay them off and retain the spend, using it as stock buybacks or exec comp.
And certainly it feels like we've seen #2 out in the wild.
Assuming that the number of people working on software you use remains constant is not a good assumption.
(Personally this has been my finding. I'm able to get a bit more done in my day by eg writing a quick script to do something tedious. But not 5x more)
This. It's extremely expensive to keep core functionality like this in a fork. Every single surface that manifest v2 touches (js runtime, extension hosting, permissions, network, APIs, chrome even) that gets changed upstream has to be redone to account for v2. Every new system built into Chrome that only works with v3 has to be effectively back ported to v2.
The only other option is to keep v2 in chromium itself and have Chrome disable it... While still paying the cost of supporting it in all new feature dev.
There's no world where Microsoft spins up a new engineering team solely to deal with the extra cost of keeping v2 around.
That said this sucks. I got my first internship on the Internet Explorer team by talking about how hard it was to install an ad blocker in IE, compared to Chrome.
No one cares for specifically V2, it's just V3 is intentionally crippled. Just allow functionality required for more feature-rich extensions like uBO and everyone will forget V2 very fast. V3 does allow extensions to monitor and sell network data (no privacy improvements), but blocks modifications (no cutting out ads)
It's worth noting that many of these are service agreements, not just data. It's tailored/specialized forecasts that are being built for the customer, not simply selling them the data they give to the public for free. So doing additional work for a fee, not monetizing existing data.
It's funny. We get up in arms because our boss's boss's boss wants to decide if the work we're doing this sprint is valuable - there's no way they can begin to understand what it is they pay me to do here! They've got dozens or hundreds of reports, no way they can decide if fixing this CSS bug is the best use of my time.
And then people think they can decide if the radar station detecting low altitude systems near Palau is a good investment or not.
A bad boss limits everyone's abilities to what the boss understands and can do. This governing approach limits world-class scientists to what the public understands - which is essentially the tactical argument made by the GOP: It looks useless to you and me and that is our source of truth! Are you condescending elites calling us dumb?
The Dems are complicit because in about 25 years, they haven't bothered to come up with a simple, effective counterargument.
I don't know anything about weather data. I couldn't imagine overseeing these scientists or their technology.
>The Dems are complicit because in about 25 years, they haven't bothered to come up with a simple, effective counterargument.
Because no counterargument, however simple, would be effective. Republicans mistrust "elites" and "academia" and "education" and "science" as a function of their own persecution complex and conspiratorial worldview. And yes, it does make them dumb - aggressively, proudly dumb. A lot of them want NOAA gone because they associate anything weather related with what they consider to be a vast left-wing climate change conspiracy. These are the same people who harass meteorologists because they think they control the weather. There's just no way to argue with that.
> Because no counterargument, however simple, would be effective.
Please pardon directness, but to get to the heart of the matter after years of these helpless arguments (and in reference to Democrat officials, not to the parent): What a bunch of losers.
This problem isn't even hard on the scale of life and politics. The #1 problem - possibly the only real problem - is their loser attitude. Who ever accomplished anything with that attitude. The GOP, in constrast, thinks the impossible is possible, never stops and barely slows down after each catastrophe, after Trump's loss, after Jan 6 ... and they have transformed the country and the world.
At least SV and HN should appreciate that. And IMHO, the constrast between the two is where much GOP support for their insanity comes from. Who supports whiny, ineffectual, helpless leaders? What's even the point? Imagine the support someone with courage, capability (including effective communication and charisma), and a plan to win would instantly garner.
Wow, I have never heard so many excuses, and never seen excuse-making so widely accepted. To make excuses was shameful in my experience - until recently!
Never give up, said Churchill, with the Nazi military controlling continential Europe and bombing London, and most of his fellow leaders thinking surrender inevitable. Washington led the US military through the darkness and utter despair of defeat, starvation and Valley Forge:
https://news.ycombinator.com/item?id=43022337
Now victimhood and powerlessness are everywhere and your enemies could not dream of better. You outnumber them, but you put down your arms and complain.
Is this something like inverse gell-man amnesia? You're aware of the value noaa provides so you're skeptical about removing it, but when we turn the page to talk about another agency removal makes sense again?
Not attempting to dunk, I should say, but wondering how this gets modeled and if there's actually a discrepancy there
Right, I think we're going to find that a test of "Does this sound like a waste to an uninformed person who has thought about it for five seconds" is a pretty poor framework for making sweeping changes.
Not a fan overall of what DOGE is doing, but I disagree with your line of reasoning here. Obviously not all government agencies provide comparable amounts of value to the general public based on the resources they consume. Does one have to be an expert on the inner workings and initiatives of each of these organizations to have an opinion? Maybe, but that doesn't seem practical, outside of having some large oversight body employing many people to review this... which is just what DOGE purportedly is.
Now, is the current DOGE proceeding to do this in a reasonable way? No. But that largely comes down your assessment of the people running it, not anything implicit
>Maybe, but that doesn't seem practical, outside of having some large oversight body employing many people to review this... which is just what DOGE purportedly is.
The oversight body is Congress. They hold hearings, call on experts, issue subpoenas, and represent the will of the people. Plus, because Congress defines the agencies and apportion budgets for specific projects in those agencies, they're the perfect group to do oversight.
DOGE could abide by the Constitution if it had simply conducted audits, compiled findings with suggestions, and presenting those at a Congressional hearing. They should not interfere with agencies carrying out legally required duties.
It's insane how these days the "crazy leftist" point of view is that we should stick to Article I of the Constitution. We have peaceful transitions of power because the losing side knows there are still rules the winners can't break. If either side makes Constitutional crises their go-to tool, there are only two awful end-states: entrenched tyranny or violent revolution. Maybe both.
We have an existing oversight body, the OIG, which is a couple orders of magnitude larger than DOGE. And a reasonable statement you could defensibly make is that OIG isn't doing enough to curtail spending, the same way you or I aren't doing enough to prevent bugs in the code.
The only thing DOGE does, that OIG doesn't, is _not_ attempt to understand the value of the work being done.
The people in DOGE are of course a problem, but the process they're following is flawed from the get go, namely "judge programs based on the opinion of some uninformed outsiders".
As it turns out, the government actually has… the Government Accountability Office (GAO) as an agency to do just this. Agencies also have inspector general offices that focus on each of their respective agencies, too (Trump has tried to fire most of them, illegally). Congress also has the Congressional Budget Office (CBO), which provides Congress with budgetary advice independent of the Executive branch.
The US Government is too large to be perfect. But I suspect it probably works far better, at scale, with less variance, and more nuance, than many HNers imagine.
>But that largely comes down your assessment of the people running it, not anything implicit
Nonsense. The very WAY doge is doing things is bad. You cannot safely shut any large body of human effort down in just a few days and not end up causing damage.
Same thing with deportations. You cannot do deportations en masse without people losing their rights or innocents being hurt.
Less technical here doesn't neccesarily mean "worse engineers". It can also mean lawyers, marketing, sales, product, and leadership.
Someone is trying to learn something from you and you give them an answer so full of holes and caveats that it looks like fishnet stockings, you haven't imparted any confidence to them in your answer.
When someone asks you if you can commit to delivery in the upcoming sprint, they aren’t trying to learn from you.
Also, caveats are valuable information. Yes, we can go live next week if the number of users remains under x until we complete z. Clear communication empowers decision makers. Intentionally omitting trade-offs and limitations that are relevant means you’re being misleading.
In a literal sense it's easier, safer, faster, etc for an LLM to remember "use server Foo to do X" than "I read a document that talks about calling api z with token q to get data b, and I can combine three or four api calls using this http library to...."