HN user
in the age of agents I found myself loving frontend again, loving devops again, loving email servers again, you name it, I suspect in most cases those roles will merge into one (excluding the ones needing extreme competency and trust).
You say it's performative joke, but it all depends what you're using model for. So far the rule has been quite straightforward, better models consistently renders pelican in higher quality, I've yet to see an exception. It is also a good enough (for me at least) test for "taste" the model has.
they're comparing to similar capability llm models, not humans. If one dishwasher does job at similar quality as another dishwasher, but using 30% more water and energy, you wouldn't compare to how much it costs human to do the same work, it would make no sense.
Tailwind is the worst form of CSS, except for all the others.
just link it?
but why? pressure from competition?
oh, I read fable as a story, fable cut meaning you can stitch up stories which is a form of storytelling, so quite fitting for video editor
Cannot relate, my expectations might just gone up, because when I compare what I was producing with agents a year ago vs now, it's night and day.
especially when using /humanizer is one prompt away
okay squidward, stuff from 20 years ago that seemed magic being replicated today with technology is unremarkable and children are just too dumb to understand how boring this is, we get it
Not all "utterly democratic humane experiences" are desired, so why not.
depends if you look through China citizen point of view or someone in the west
that's quite interesting because I would love for AI to run my systems, given it is capable enough (and it is given right tools). Jarvis anyone?
think of genetics like functions
I do the same, and it's mostly because I use one type of human communication to both communicate with people and to provide inputs to llms - and I'd rather not have to "mode-switch" between the two, so keeping same style of mannerism is easier to manage as it lets me focus on my requests instead of thinking how to sound more robotic to save tokens.
sounds like vscode issue more than anything else
your comment with "I use Ai" is as useful as saying "I eat food and it's not the best". Details matter
Russia would love for telegram to be Russian app, unfortunately for them, there is nothing to suggest that's the case as plenty of examples why it's not (one being that tg is banned in Russia)
now yes, it's no longer 2005
word "her" in this context gave me heavy feelings, what makes one to pick such a career move...
few years ago they weren't
rich of you to talk about slop when your own 'handwritten' project has one c file with over 6.5k lines of code.
they might be critical in public, but they still provide a lot intel
you mean /security-review ultra, given their current way of handling commands
they're not wrong though
that just sounds petty for the sake of pettiness, surely you can do better in terms of mocking
how to say you haven't tried llms since 2023 without saying it, that's quite literally one of the things they excel at
makes sense, if you want your product to be good, you need to dog food it
okay I'm now intrigued, what was the outcome?
been using my own vue inspired library @yiin/reactive-proxy-state in backend environments with lot of joy and was thinking if the time will come for some new language to have reactivity as first class citizen, I guess this is a step towards that, interesting to see.