If Claude Code or Cursor is actually that good then we're all unemployed anyway. Using the tools won't save any of our jobs.
I say this as someone who does use the tools, they're fine. I have yet to ever have an "it's perfect, no notes" result. If the bar is code that technically works along the happy path then fine, but that's the floor of what I'm willing to put forth or accept in a PR.
> If Claude Code or Cursor is actually that good then we're all unemployed anyway. Using the tools won't save any of our jobs.
There is absolutely reason for concern, but it's not inevitable.
For the foreseeable future, I don't think we can simply Ralph Wiggum-loop real business problems. A lot of human oversight and tuning is required.
Also, I haven't seen anything to suggest that AI is good at strategic business decisionmaking.
I do think it dramatically changes the job of a software developer, though. We will be more like developers of software assembly lines and strategists.
Every company I have ever worked for has had a deep backlog of tasks and ideas we realistically were never going to get to. These tools put a lot of those tasks in play.
> I have yet to ever have an "it's perfect, no notes" result.
It frequently gets close for me, but usually some follow-up is needed. The ones that are closest to pure one-shot are bug fixes where replication can be captured in a regression test.
> Every company I have ever worked for has had a deep backlog of tasks and ideas we realistically were never going to get to. These tools put a lot of those tasks in play.
Some of that backlog was never meant to be implemented. “Put it in the backlog” is a common way to deflect conflict over technical design and the backlog often becomes a graveyard of ideas. If I unleashed a brainless agent on our backlog the system would become a Frankenstein of incompatible design choices.
An important part of management is to figure out what actually brings value instead of just letting teams build whatever they want.
> If Claude Code or Cursor is actually that good then we're all unemployed anyway.
I don't know about that. This PR stunt is a greenfield project that no one really knows what volume of work went behind it, and targeted a problem (bootstrapping a C compiler) that is actually quite small and relatively trivial to accomplish.
Go ahead and google for small C compilers. They are a dime a dozen, and some don't venture beyond a couple thousand lines of code.
If they fly low enough that I could hit them with a shotgun, they're on my property. This isn't true of planes and helicopters.
These things aren't planes or helicopters and poised to be much more invasive and annoying, why people act like they are just like a passenger airplanes flying a literal mile overhead is baffling. But to that end if Amazon started making deliveries by landing a fucking helicopter in my yard on the regular I would also want them banned.
We're talking about allowing an "essentially" generic version of an existing FDA approved drug made by licensed compounding pharmacies that has been legally distributed for years due to the shortage. If it's safe enough for people to take in a shortage then it's probably safe enough for people to take in a not shortage.
As always, depends on the law. This is a bright line example of companies breaking the law to the direct tangible benefit of not only their customers but the population at large. Letting Novo Nordisk jack the price back up and deprive the vast majority of Americans access to the greatest good to public health in a century meanwhile is… maybe not the example you should be holding as the law working.
Yes, bootleggers can undercut legit competitors, providing a boon for consumers.
In this case, Novo developed the drug. In your view, why does Hims get credit for "the greatest good to public health in a century" and not the company that sank over $10B into developing Ozempic?
Of course, Novo faces competition from Lilly and every other pharma company in the world and continues to lower prices in the face of this competition.
And they provide a valuable service to their customers, I have a very positive association with various drug dealers I've had over the years. Say what you want but they're literally out on the streets serving their local community. For a more HN example, people in the real world are extremely pro piracy and view the people cracking DRM as doing a public good.
I fully expect the state to take action against the, to me, very obvious will of the people who are actively seeking out and purchasing these products. Clearly folks don't respect the legitimacy of IP rights in the same way they respect property rights since nobody blinks when buying compounded GLP but at the same time wouldn't shoplift at their local BestBuy.
So yeah the government's response isn't surprising but you won't see me cheering them on, and I don't think you should either. You literally stand to lose from it.
Because the point is for the AI to take the prompt, figure out what that prompt means in the context of the code base, and then make an issue that provides additional information.
It's asking the AI to takes its best guess at what you actually have to do to solve/implement the issue using the code that already exists.
Sure, but Google isn't maintaining two sets of documentation here, the MCP server is just a thin wrapper around the webpage with a little search tool. So it's still the docs for humans just with a different delivery mechanism. Which is fine, but you can understand when hypertext exists largely for this exact purpose folks would find it odd and over complicated to reinvent the web over jsonrpc for robots.
This article is super weird because it's looking at an issue from orbit where the only things you can see are vague things like "funding" where the problem is on the ground and probably can't be solved by the levers available from orbit. The lesson of funding having arguably no effect on outcomes should either be that we genuinely don't know what improves outcomes or that we do but schools are lighting money on fire buying other things.
It means the problem is unfortunately local and you have to actually go to the schools and see what the issue is. Based on what my former HS spent money on I figure we will eventually find some commonalities:
* New computer labs, laptops, digital textbooks, learning software licenses, smart boards, and other and other expensive crap that is at best neutral from a learning perspective.
* Pointless building improvements that don't service education but instead service the prestige and egos of the administrators of the schools.
* Chronic long-term understaffing and light-speed "just get through it" lesson plans that makes teachers not give a shit, and powerless to do better even if they do.
I think "just blame the administrators" is too easy a cop-out because I've yet to meet one who isn't also underpaid and dying of stress. Although maybe I just don't have access to the real higher ups.
>> * New computer labs, laptops, digital textbooks, learning software licenses, smart boards, and other and other expensive crap that is at best neutral from a learning perspective.
I think we should be actively removing these things from schools, but it's a tough fight as parents against an entire well-funded EdTech industry pushing these things with a firehose of VC money.
>> * Pointless building improvements that don't service education but instead service the prestige and egos of the administrators of the schools.
This makes me crazy. We have a very fancy, very large new school building my city which is LEED platinum certified. I can't possibly imagine that that certification level is cost effective. I'm sure we could have built a very good school with a healthy safe learning environment and environmentally conscious decisions for heating, cooling, power, etc. for significantly less if the city were willing to forego the press release headline. This is also a really hard problem that pits taxpayers against a well-funded industry full of lobbyists.
Both of these can be traced back to the principal agent problem, which really is blaming the administrators, because they're making decisions and then don't have to deal with the consequences (actually integrating and using EdTech in a classroom, paying more taxes for the same or worse education, etc.).
I would love for folks to start packaging their software for major distros if for no other reason than to see just how annoying the tooling is to use.
reply