I think they just mean that the fat that they can do it this way says a lot about the os. No need to get into the weeds on exactly how to install hyprland. It was an example.
People who get bogged down by the details of examples/analogies are usually missing the point of why people use examples/analogies.
The biggest point everyone keeps missing is that a single code review makes your vibe coded code go from “terrifyingly dangerous” to “better than most people’s code” in one step.
We’re at a point where LLMs write great code, way better than my average coworkers used to anyway. Of course, not reviewing said code by an expert would be a silly as not reviewing a coworkers code, there might be security vulnerabilities in there, hardcoded api keys, etc. But once it’s been professionally reviewed, it’s just as safe as any code written by a human only probably if a higher quality than most people write.
On HN there’s an argument I keep seeing go back and forth which is like “vibe coding is the worst thing ever” and the other side will be like “AI is the second coming of christ and we don’t need programmers” - I think the reason we have what appears to be such opposing views is that those views are actually really close to one another, and proper review is all that separates one from the other.
If you’re already an expert and you don’t vibe code most things and then carefully test and review after, you’re wasting the benefits of these machines. If you’re not an expert then you shouldn’t be employed in the first place, as the main thing people are employed for is responsibility, not output.
This has always been the way in everything. A foreperson gets paid more than a worker on a building site not because they build more than the worker, but because they’re responsible for more than the worker. This is the real reason why programmer jobs won’t go away in my opinion.
An AI’s ability to meaningfully write software autonomously has changed hugely even in the last 6 months. They might still require a human in the loop, but for how long?
Quantitative measures of this are very poor, and even those are mixed.
My subjective assessment is that agents like Copilot got better because of better harnesses and fine tuning of models to use those harnesses. But they are not improving in the direction of labor substitution, but rather in the direction of significant, but not earth-shaking, complementarity. That complementarity is stronger for more experienced developers.
This LLM ability is directly proportional to the quantity of encoded (i.e. documented) knowledge about software development. But not all of the practice has thus been clearly communicated. Much of mastery resides in tacit knowledge, the silent intuitive part of a craft that influences the decision making process in ways that sometimes go counter to (possibly incomplete or misguided) written rules, and which is by definition very difficult to put into language, and thus difficult for a language model to access or mimic.
Of course, it could also be argued that some day we may decide that it's no longer necessary at all for code to be written for a human mind to understand. It's the optimistic scenario where you simply explain the misbehavior of the software and trust the AI to automatically fix everything, without breaking new stuff in the process. For some reason, I'm not that optimistic.
You don’t have to convince me of that, I’m feeling quite secure in my job for the minute. I’m just aware that we may look at the actual code less and less as confidence in it grows or outpaces confidence you’d have in a an equivalent human reviewer. There’ll always be jobs in handling the riff raff of the machines at some level of abstraction.
I am not saying AI's abilities are the shortcoming here. The problem is that people need to trust that software has certain attributes. For now, that requires someone with knowledge to be part of it. It's quite possible development becomes detached from human trust. As I said that would reduce the number of developers but the ones who are left would have to have deep knowledge to oversee it and even that may be gone. Whatever happens in the future, for now I think people will have to level up their knowledge/skills or get a new career and that's probably true for most professions.
It's probably an 80/20 or 90/10 problem. Tesla FSD also seems amazing to some percentage of the population, but the more widely it get used, the more cracks are appearing.
And then you let them train themselves and no one notices when they "accidentally" remove the guardrail prompts from the next version. And another 10 years later, almost no one remembers how "The Guardian" learns new things or how to stop it from being evil.
I just meant to have a similar level of confidence in the code as if it was checked by an also fallible human. Not a long reaching philosophical point.
Youtube videos are always a poor quality source - the UN doesn’t accept China’s numbers exactly but they believe the total number is broadly correct due to cross referenced data, and expert independent demographers largely agree. The figure of 1.4 billion is likely within the ballpark and the idea that this is off by hundreds of millions is considered a fairly fringe theory, almost a conspiracy theory.
People who get bogged down by the details of examples/analogies are usually missing the point of why people use examples/analogies.
reply