I'm an atheist, but if there's a God then I am grateful to her for granting me the wisdom to pay off my house before retiring instead of investing that money in some horseshit.
Its a shelter from storms, both physically and metaphorically.
My mental model of the 'new normal' is end users using AI to get their work done.
So if I re-worded the OP's description and replaced 'internal tools' with 'internal AIs' then this would at least seem like a more reasonable process to me...
> At our startup, engineers don't build features anymore.
> They build APIs that internal AIs can connect to.
> Most "features" like running an SQL query, sending a push notification when product X is ordered gets built by ops or product folks using those tools.
To me this describes a team of engineers that use AI-capable tools and that are building 'features' for themselves.
In the way that us dinosaurs used to write build scripts.
I'm not saying that my mental model is right or wrong, just that working this way seems reasonable if you buy into my model.
> This is the single most impressive code-gen project I’ve seen so far. I did not think this was possible yet.
To get that sort of acclaim, a human had to build an embedded programming language from scratch to get to that point. And even with all that effort, the agent itself took $631 and 119 hours to complete the task. I actually don't think this is a knock on the idea at all, this is the direction I think most engineers should be thinking about.
That agent-built HTTP/2 server they're referencing is apparently the only example of this sort of output they've seen to date. But if you're active in this particular space, especially on the open source side of the fence, this kind of work is everywhere. But since they don't manifest themselves as super generic tooling that you can apply to broad task domains as a turnkey solution, they don't get much attention.
I've continually held the line that if any given LLM agent platform works well for your use case and you haven't built said agent platform yourself, the underlying problem likely isn't that hard or complex. For the hard problems, you gotta do some first-principles engineering to make these tools work for you.
Do you have any of those examples handy by chance? Curious to check them out. And agreed! While coding has become a commodity - programming is still as alive as ever.
Absolutely agree with that last sentiment. Recently I came across a project by a former google engineer called Dyad: https://github.com/dyad-sh/dyad
This is built to be a lovable/bolt alternative and is definitely on the early side in terms of total capability and reliability. But once you start digging through the source you realize how much engineering actually went into building it. Not just chaining prompts together in a dart throwing exercise and praying for a good result.
This is much closer to the "turnkey" solution vertical I mentioned in my earlier commentary, since its meant to generically build any web app, but there's a few applied concepts that are shared with the promptyped approach used in the HTTP/2 server (though not as sophisticated when compared to the category theory / type theory approach).
I think it's a good example to work backwards from though, if you peel the onion a bit you realize how much more tightly you could scope this for more bespoke projects.
>> But nothing has the quality of life impact of smart blinds <<
I have a ton of sleep problems and just wanna push back here a little... going for a brisk walk in the fresh air and sunshine every day works a lot better for me.
This decision only makes sense it saves more lives than the number of lives that will be lost because of it.
It seems to me like it should totally be possible to do the math here and figure it out. Compute the lives saved and compute as many of the lives that will be lost.
For instance, statins are a risk to pre-diabetics, and to children, and to etc...
There better be a very large difference.
That's the bottom-line argument that I would have attempted to make.
Its a shelter from storms, both physically and metaphorically.