disclosure: I work on the team behind noq. Can't emphasize enough that the quinn maintainers are really lovely people, and quinn is an excellent project.
"Requirements" are a spec. If your requirements lack detail, you probably won't get what you expected -- vague "requirements" can be met without solving your problem in many cases.
It's okay if you don't get what you expect as long as it works. That's the point. There's a ton of different valid permutations and letting a LLM pick a good one ends up working in practice.
> When one prompts an AI to "write me a to-do list app", what they really mean is that "write me a to-do list app that is better that I have imagined so far", which does not really require detailed spec.
What does "better" mean here? i suspect that "better" would be defined...in a spec
They do not. I review a ton of code, and while the quantity is going up, the quality of that code is getting worse. LLMs only make developers more efficient if they skip the due-diligence required to verify its output; they all say they don't, and almost all of them do.
The economics of software development have lowered the bar for software engineers: there simply aren't enough people who are good at it (or even want to be), and the salaries are very high, so plenty of people who shouldn't be SWE's are.
I am a software engineer, and I would absolutely love to see more professional accountability in this field. Unfortunately, it would make the cost of software go up significantly (because many many people writing software would be ejected from the industry)
Eh, a think tank usually has some kind of minimum requirements, such as education or industry experience. The usefulness of hackernews lies in "farming the opinions of the kind of dork that hangs out on hackernews" -- this is useful data, but "crowd sourced think tank" is trumping it up a bit i think
Eh, a think tank usually has some kind of minimum requirements
When paid for, I agree that is absolutely true.
When nearly free, thanks to team Daniel it's an input that can be weighted against paid options. The free but large crowd may have thought of things that paid think tank members members holding doctorates may not have. Great ideas are missed all the time and most often until it is too late. There may only be a few golden eggs and many bad eggs but there are quicker ways to sort that out nowadays without an Eggdicator and Oompa Loompas though I do miss the songs. One golden egg could pay for the entire cost of the staff running HN for a decade.
The only time i use a VPN is when i'm traveling and I don't trust "free coffee shop wifi"
I probably won't use Mozilla's offering, because i want any VPN to cover the whole system, not just the browser (correct me if i've made a bad assumption here)
reply