What's it been like managing a fairly large project with Zig? I know you've spoken highly of the language in the past, but recently it seems like Zig has been through some substantial changes that would be relevant to a terminal emulator. I'm curious how painful the churn has been for project maintainers.
What the fuck are people working on where it's possible for the LLM to just add entire features. Refactors and class/method level code can be impressive, anything highly structured with good guard rails. As soon as things start to reach beyond that it falls to absolute garbage.
I want to hear someone say "I work at Google on a 10yr old 100KLOC service and AI is doing it all we are just vibe coding" as that would be really interesting. Greenfield yeah AI slaughters greenfield before breakfast
There are companies building entire applications, indeed replicating the functionality of existing SaaS applications to test their original applications,with no humans in the development loop.
We're looking at the twilight of programming as a human skill. The LLMs are just that good.
The end result is, and will always be garbage if there is no "human in the loop" to test whether the result meets the requirements, and telling LLM what to do if it doesn't.
Like somebody else said, there is still a need for QA (and usually for requirements gathering too), that's a part of the development cycle. Developing software that is meant to be used by humans with zero humans involved isn't realistic.
I mean... It takes 10 minutes of testing to know this is bullshit. At least in the near term. I've sat with an agent and played the part of a vibe coder. Not looking at the code, frankly providing more guidance and feedback then a vibe coder could, and even in a thousand line app it falls to absolute shit fast. It does get something that "technically" works, but it will collapse in on itself in no time.
The act of designing software might be changing, less writing the actual code, but someone who knows what the fuck they're doing still has to guide the ship.
That's why there's been such a massive effort to position LLMs as critical to national security. If they can make themselves big enough and critical enough (even in just perception) to the government they won't let them fail. They'll let individuals lose their livelihoods of course, since it's rugged individualism for all of us lowley normal people. But corporate socialism will keep the big players afloat.
I'm saying, in an admittedly flippant way, that anyone seriously talking about AGI or treating stuff like this as anything more then a publicity stunt doesn't need to be taken seriously. Anymore so then someone who says the moon landing is fake. You just smile and go on about your day.
That being said, given were on a tech forum there's probably a 50/50 chance most comment are from bots. Shit for all you know I'm a bot.
The "This is the key insight -" or "x is where it gets practical -", are dead give aways too. If I wanted an LLMs explanation of how it works, I can ask an LLM. When I see articles like this I'm expecting an actual human expert
An article written by an expert is nothing like this. You might be able to get something similar out of an LLM but it's gonna take a lot more effort then was out into this.
That's about right, my estimate is 50% to 70% depending on case.
On the other hand, isn't it clear that people will be more productive with whatever agent they have experience with? That's my reason for going with open source agents and the attempts of Big LLM to kill that workflow only reaffirm my decision.
I had trouble taking the article seriously after this
"Anthropic did not partner with the Pentagon to make money. They did it to help. They did it under a mutually agreed upon contract that Anthropic wants to honor."
The only thing Anthropic cares about is money. There is no other motivation for anything it does, military or otherwise.
Seems like you and the author are doing the same thing: speaking in absolutes. It's possible for "Anthropic" (or the summed vector of all the human decision makers within it) to have contracted with the military because it wants to make money AND it wants to help.
The questions are: "Help with what, precisely?" and "How much money versus how much value (/principles) compromise?"
I've worked for big corporations for a long time, and one of the first things I've learned is that individual motivations mean very little, if anything. At the end of the day, the bottom line is all that matters. And we know this is particularly true of big LLM companies given their track records.
The community college I went to was doing this same crap. I remember going to the opening of a new arts building that provided less usable space then the building it replaced, and sitting around with all the donors and school administration paying themselves on the back. Meanwhile they didn't have enough room for most of the departments, and the tutoring programs were getting slashed.
I'm still confused by why anyone wants to use either Docker or Podman desktops. The the docker/Podman CLIs seem like a much better way to interact with containers/images. Maybe it's just my usecase.
I can't speak to docker, but the Podman desktop UI on MacOS doesn't really offer any functionality that the CLI doesn't. It's more like a status dashboard than anything else. I personally never look at it. I don't see how you can get very far managing containers, images, etc using _just_ the UI in any case.
Agreed. To be honest I feel the same way about k8s. A bunch of people on my team get grumpy if we don't have k9s available or some other interface, but I prefer to just use kubectl
I personally use Docker Desktop because it was the easiest way to install Docker on my Mac. I launch Docker Desktop, close the window but keep the app running in the background, then use the docker tool on the command line :)
Given that they built their businesses on wide spread copyright infringement and licence violations, I couldn't give less of a shit about people turning around and "stealing" from them
reply