This reads so well I was supposed to go out for a workout but I couldn't stop until I finished it.
Incredibly engaging yet simple writing that flows well.
A lot of words, but essentially says nothing useful.
If GitHub is the wrong shape for this new world. Well, show me a hint of what the new world should look like?
To me it seems like everyone is frustrated, mostly at how fast things are changing, but not necessary because the existing tools suddenly became trash/irrelevant.
A lot of us are still contending with the fact that large amount of code is being produced and we don't know what the fuck to do about it. And we're less intimate with the code and product we ship than we were before.
My personal take is that if you want to scale in engineering you really only have 2 options.
1) you start acting like a senior staff level engineer and you stop caring so much about implementation and start caring about the things that actually matter, the architecture, the performance profile, the scalability, the test coverage, the monitoring, the velocity of development, etc etc.
Or 2) you don't scale.
LLMs can write 10k lines of code per day like its nothing. You can't review that with a jade handled magnifying glass and keep all that in your mind. After a few months, you could easily have 250k lines of dense production code + much more in tests and tooling etc.
You either have a team of people to watch over that, or you don't. You're not scaling yourself to be able to review all that and keep it all in your mind.
If other people are scaling, and you're not, you're unlikely to do as well as them. BUT, it's not impossible if you're really good. Being really good scales way less than using LLMs effectively.
Google doesn't work because they rely on hope that every person they hire doesn't do things they shouldn't. It works because they make it nearly impossible to do things you shouldn't. You need to build systems as well. Or you don't. Just do it the old way.
> you stop caring so much about implementation and start caring about the things that actually matter, the architecture, the performance profile, the scalability, the test coverage, the monitoring, the velocity of development
What architecture doesn’t care about implementation? What performance profile doesn’t care about the details of the implementation? What does the test coverage is about if it’s not the implementation? What are you monitoring? The specs or the implementation?…
Not caring about the implementation seems like not caring about the materials when building an house, with eyes stayed only glued to a novel’s like description of the house.
I think you misunderstand - it’s not that you shouldn’t be capable of evaluating and improving the implementation, but that it’s usually irrelevant. A very large majority of the time, “good enough” is fine. Fix things people complain about, and use the rest of your time to do more important things.
The problem I see is that in a traditional company a senior engineer would push back on complexity and know when to do due diligence.
AI seldom pushes back, embraces complexity, does a lot of due diligence (however often superficial), and then completely misses the point and lays a trap on the code.
It’s not nearly as trustworthy as an actual team of humans.
I couldn't agree more. I've been building something that is trying to solve this problem, an abstraction layer for code that you, your agents and co-workers can all use together. I would love the chance to talk to you and get feedback if you're willing.
I'm not familiar with SteamOS and Valve hardware in general. Could I play something like Overwatch on this, and connect keyboard and mouse? Could I play other PC games like World of Warcraft?
It's just a Linux box, you can do anything that you can on any other Linux machine (including install Windows).
Linux more or less runs most Windows games. The ones that don't run are ones where the developer is going out of their way to make them not run - mostly with kernel-mode anti-cheats that just find themselves staring at the wrong kernel.
Steam makes that pretty seamless and Steam games "just work". For non-Steam games you need to do some tinkering, it's stuff that most people browsing this forum can do.
Note that the "just" is overlooking that it's more locked down than a typical Linux box, in that the OS filesystem is read-only and all app installs live in userland (though you can turn off the read-only behavior). For what it's worth I'm very much a fan of it as a default for a mass-market machine, but you'll run into weird gotchas if you want to do "programmer stuff" with it.
That's how a lot of modern Linux distros are because immensely better. Updates on an immutable OS are massively more reliable, it doesn't prompt you to merge diffs in config files, it never breaks, you never have to reinstall.
I've run Bazzite on my desktop for the last year and every update has just been hitting the "Apply" button in the settings page with my xbox controller. While on mutable distros it's always involved going in to the terminal and running a series of commands or opening the repo list and manually replacing the release name for Debian. I know there is a GUI software store to do it but it literally never works because some error will show up that isn't handled and you just get a generic error message.
I'm super confused as well.
This seems like exactly that, just some default prompt injections to chose from. I guess I kinda understand them in the context of their claude chat UI product.
"AI" companies have reached the end of the road when it comes to throwing more data and compute at the problem. The only way now for charts to go up and to the right is to deliver value-added services.
And, to be fair, there's a potentially long and profitable road by doing good engineering work that was needed anyways.
But it should be obvious to anyone within this bubble that this is not the road to "superintelligence" or "AGI". I hope that the hype and false advertising stops soon, so that we can focus on practical applications of this technology, which are numerous.
Antisemitism is a form of bigotry, no more or less special than other forms of bigotry and racism.
If you read any significant amount of history you'd know that already, and you wouldn't need to prove that Antisemitism is real. Of course it is. So is anti-[insert religious or ethnic group]
Added support for GPT 2.5
http://batchbanana.com/
reply