This should be trivial if you have proper API documentation in something like swagger. You can generate a cli tool with no "figuring out" anything either.
Nothing is “trivial” when you combine humans and computers. I worked at the MIT Computing Help Desk during my undergraduate years. We joked that we received callas from Nobel laureates who could find subatomic particles but couldn’t find the Windows Start button.
My company is currently trying to rollout shared MCPs and skills throughout the company. The engineers who have been using AI tools for the past 1-2 years have few, if any, issues. The designers, product managers, and others have numerous issues.
Having a single MCP gateway with very clear instructions for connecting to Claude Desktop and authenticating with Google eliminates numerous problems that would arise from installing and authenticating a CLI.
The MCP is also available on mobile devices. I can jot down ideas and interact with real data with Claude iOS and the remote MCP. Can’t do that with a CLI.
It really does feel like the tech right has disappeared over the last year, at least as a more grass roots thing outside of the actual billionaires themselves.
The early crypto and tax victories were presumably the impetus for many, and that's already been realized. There's not much incentive to stick around and be a bad faith advocate for incompetence and graft when you've already got yours.
In my impression the billionaire worship is just another form of fundamental respect and enforcement of hierarchy that has been part of conservative politics forever. We are back to transparently the "right" leaning being wanting to keep the absolute monarchy.
Yep, it's easier to ask forgiveness than permission. It's far easier to undo the 1% of the time they fuck up in a serious way than it is to manually audit and allow an the routine stuff.
The key is to only give them access to things you're willing to lose.
This is also why giving them any kind of direct write access to production is a bad idea.
If you arent manually auditing, you only notice the fuck ups when they’re instantaneous
If you don’t trust it to interact with prod, but still trust it to write code that will run on prod… you’re still trusting it with write access to prod.
The only thing I’m willing to let Claude write for me is a static site generator, because static files without JS aren’t going to do any damage, it either loads or it doesn’t.
To be clear, I'm not saying you can't (or shouldn't) review the results, only that you can (and should) give the harness the ability to do everything it needs to function without hitting permission barriers that need to be manually approved.
The correct way to run these safely is to sandbox them so real lasting damage is impossible, not to micromanage individual access requests.
If you are a team lead or above, do you manually audit every line of code that other developers on your team write even when you are the one that will ultimately be held responsible? Every library you use?
This was fairly routine when the pace of everything was slower, we didn't have a giant tree of dependencies, and companies cared more about product quality.
Right, so a team lead with seven developers - or are you claiming that’s an outrageous scenario back in the old days (mind you I’m 51) - could review every line of code by everyone on his team?
It seems like a huge self own but he benefits from an extremely loyal fan base and a militaristic culture that loves rallying around the flag.
Does he even care if his actions hurt the country or global stability at all, so long as his supporters remain unwavering? It seems like he doesn't, so here we are.
There is no plausible stimulus that he might actually care to respond to.
I'll say this, coding agents make the lack of a "batteries included" framework like rails or Django somewhat less daunting.
But "convention over code" and having a default structure / shape for projects is extremely helpful and you feel it when it's missing.
For my last small project I looked at Loco but ended up passing on it because I felt like adoption wasn't great yet. I really hope it takes off, though.
> Juniors are still getting hired because they're still way cheaper and they're just as capable as using AI as anyone.
While I could buy that hiring managers believe this, it's not actually true.
The gulf between the quality of what a sr developer can do with these tools and what a jr can do is huge. They simply don't know what they don't know and effective prompting requires effective spec writing.
A rando jr vibe coder can churn out code like there's no tomorrow, but that doesn't mean it's actually right.
Absolutely agree, when we got our last junior one and a half year ago. He started with using AI for... Everything. If you told him research this and that topic and ways to do X and y and if it's possible. He just used AI which missed half the steps and information.
I'm not against research with AI. But using a search engine helps you go through a railway basically and helps you gather information step by step and you have time to notice it something is missing.
With AI you don't have the mental pause to process the information.
While I agree with what you said. In personal experience I have noticed the software design / architecture is becoming irrelevant for lot of enterprises (including mine of course). So design nowadays is about API design Input/Output/Error handling. And architecture is about Cloud/Kubernetes/APM , deployment and monitoring etc. Code now does not need much design. Things like performance, isolation, extensibility etc as those are now higher level concerns not part of code itself.
This is also where micro services pattern fits in well because individual unit is so small no design needed.
reply