30 prompts in and now it's messing up and i have to figure out at least a little bit about how all this slop works so i'll have a chance of debugging it 😂
05.03.2026 13:58
👍 3
🔁 0
💬 0
📌 0
30 prompts in and now it's messing up and i have to figure out at least a little bit about how all this slop works so i'll have a chance of debugging it 😂
when AI does all the work, the remaining value of humans will be our 'vibes' … think about that for a minute.
pretty dumb though, since i assume he in some way needs to get the thing to run, and then he's the one creating the conceptual scaffolding around it (it's art! file for copyright). i have created computer programs, i run those programs, they do stuff, they are not sole creators of their output.
100% lol
democracy is broken when the best path to a reasonable senator being elected is an unreasonable man winning the primary
There isd a problem with your Amazon Mechanical Turk account this account has been suspended by the Amazon Mechanical Turk team
hey, what did i do?
in computer use, if i say, "book me a flight to Seattle", and it goes off and does that. first off, i can't iterate because of externalities (it might have already bought it!), and it feels super dumb to iterate on it, might as well do it myself. "yeah, like that one, except make it leave earlier"
yeah, but i don't entirely believe that explanation. i think we humans are more forgiving of iteration in code, because code/debug loops are what we always do.
the other part of it is that people have more unstated opinions about what they really want the computer use agent to do, especially as more information is revealed. in coding agents, kind of just want it to work, and again feels natural to refine w/ another prompt after it does a first pass.
it's not at all obvious to me why coding agents seem to work better than computer use agents.
my theory is that it feels kind of natural to prompt and re-prompt code as you work toward a solution. but, it feels absolutely stupid to prompt and re-prompt UI to buy a product on a web page.
It might even be great if everyone is trying to create something or someone else already created 8000 times, or terrible because they’ll be repeating the mistakes that have been made 8000 times
"Workers did not use AI to finish earlier and go home. They used it to do more. "
www.ivanturkovic.com/2026/02/25/a...
i hope that's true, many people have repeatedly put their faith in a very unreliable and self-interested man, despite decades of evidence that he is not worth it.
no one rising up in Iran should think Trump will actually be there to help them if they don't succeed quickly, and especially not if they fail
www.nytimes.com/2026/02/28/u...
i have to say, even i didn't expect Trump's two big "accomplishments" to be pass a giant tax break for the wealthy and start another big war in the middle east … george trumpia bush
I personally like it, very clean, although they do let you have unlimited appendix so you could put more things there
when you start seeing spines, you start to wonder if the overton window on going along with trump nonsense is breaking …
this is a good move by Anthropic, both because they are right, and also because it makes me feel better about them
www.nytimes.com/2026/02/27/o...
LLM-based technology is good for many things, but it is not a reliable tool for autonomous weaponry. LLMs require large GPU computers to operate; you can't put them on standard military platforms, and certainly not on drones.
HCII faculty Jeffrey Bigham, Laura Dabbish & Chris Harrison are part of the 2026 CHI Academy cohort, an honorary group of people who have made substantial contributions to the human-computer interaction field. Congrats!
Details: https://hcii.cmu.edu/news/bigham-dabbish-and-harrison-join-chi-academy
with #uist2026 returning to fixed page limits and two column format, i feel like this is a real Paul Bunyan moment for me -- will my paragraph shortening skills stack up in the new LLM era??
humans are amazing storytellers; just look at all the stories we're telling about AI
i can't read the article, but what's the gist as to why they are doing this? i mean, don't they have 1980s classic "war games" in their training data somewhere?
sounds like he is fake retiring like many academics.
kind of amazing how many people are still on X
just me, listening to 80s rock, having a nice chat with claude code, "how was your day?", "oh, wow, mine too!", "wow, that worked, we're a great team!"
this is the kind of innovation we need
my first car is a plugin hybrid minivan, which is perfect for us on these trips, and day to -day, i don't use gas at all. chrysler is phasing out the last one of its kind though :(
if i drive to my folks' it's like 200 miles, which is fine, except they don't have a fast charger, so i'm probably looking at stopping for at least 30-40 minutes along the highway for a charge, maybe during the visit if i want to drive somewhere while there.
kind of a midwest cultural thing to do long drives, maybe switching over drivers. folks can argue that it's not a good idea, but if they do that then arguing in favor of EVs becomes an argument that they shouldn't drive long distances, which sounds like scolding