> An AI helps fill in the story from there. Fact checks each claim, connects the dots, makes it comprehensible.
I think this certainly has some value but this claim in and of itself is stated like your hand-wavy step 3. How do they fact check claims and connect the dots?
Maybe LLMs get there but currently they write in an extremely verbose manner, and things that have gotten into the context window that are no longer relevant continue to stick around (just try having it write some code, then work some of it back to simplify the problem - it will insist on writing comments about code that no longer exists).
Right now using an LLM to write documents is like taking a superhighway to travel 100 meters. Yeah you're doing a lot but is all that really necessary?
I won't deny that LLMs will never have a place in writing. But I personally don't think the current form is "the one that actually lands" (!).
Reminds me of watching my wife use her computer. I'd help her with something and realize all the little things more regular computer users just put up with. Incorrect focus, focus stealing, windows popping up behind current windows, unclear window styling, invisible scrollbars, moving page elements, unclear instructions, the list goes on and on and on.
Deleting career fields in and of itself is not a problem with technology, but when it's like the eye of sauron scouring workplaces and snapping jobs away (pardon the mixed universes), it starts to become a little alarming.
University graduates are often considered min-bar for white-collar work hiring, so if it takes 4 years to train someone, how are people supposed to decide on a career path when it takes less time than that to completely alter the workplace?
My daughter is entering her first year of nursing, a career path that she is greatly looking towards. Who says in 3 years that robotics companies don't actually deliver on their promises and completely up-end the care industry? While I think that unlikely, it's not like people aren't trying to automate nurses away.
The worst thing is that I know there's something interesting in there but I'm too arsed to take the time and decode what data the author must have used to generate that text.
Exactly, it would be so much better if they shared the prompts instead of the output, at least then we'd be able to make some sense of what they were thinking about.
Unfortunately the prompt may have been something like "investigate this bug and file an issue when you think you understand what's going on". The "better just to share the prompt" heuristic falls down when the actual underlying intellectual work was also done by the machine.
(Feel free to pretend that I used some phrase other than "intellectual work" if you dislike seeing it used to describe something done by AI.)
Yeah in that case just closing it and moving on would be better IMO. A sufficiently large fraction of the time the issues with vibeslopped code and/or analysis are bad enough once you start digging into it that it's not worth spending time on. My heuristic would be to simply ignore contributions derived from lazy prompts. I don't think there are very many healthy babies in that bath water.
So having the prompt available would be useful even in the degenerate case.
> People don't usually remember the average amount of time they wait. They fixate on those times when the elevator took FOREVER, the p90 case.
I would always get a chuckle out of seeing some poor soul waiting 3 hours to go down a few floors after work, only because I failed to add stairs to the lobby.
I spent about an hour in a VR entertainment space, where you donned a headset and played a game designed for a large play-space.
It was incredibly fun, but afterwards driving my car home I felt like the driving experience wasn't "real", and I had to put more conscious effort into my driving than usual to remain a safe driver. It took a few hours to wear away.
(This was a very distinct experience from what I have felt when binging a VR game like Half-Life: Alyx at home, where I get urges to teleport-move around my house and my hand-perception is off).
Fascinating. I wonder what it would look like if you intentionally tried to create a VR experience optimized for creating this disruption. Does every game or experience have the same effect? If not what causes a greater or lesser impact on your senses?
xda is older than github and has a lot of institutional inertia. Also I get the impression that many of the people involved in the xda ecosystem are hobbyists that just kind of learn things as they go along and have less exposure to bigco software engineering practices.
You talk as if github is a daunting service only meant for enterprise customers.
When in reality it's easy to sign up and used by almost every kind of project you can think of, including someone's 100 line random bash script with a single sentence README, a tiny embedded device hobby project all the way to a vibe coded project, from people who know nothing about software engineering. Issues are PRs are regularly used for all those projects. You almost need to go extra mile to not put your stuff on github.
I don't think there is any reasonable excuse/explanation other than "inertia".
I've been using cmux for a long time too but am pretty happy with it. It's not perfect but much better than plain tmux/ghostty. I'll give herdr a shot too.
reply