relativeadv

slop

position is one thing. implementation of that position is another.

"Forty years later, in September of 2018, I started working on this version of Space War. It's an animated GUI driven system with a frame rate of 30fps. It is written entirely in Clojure and uses the Quil shim for the Processing GUI framework." - Robert Martin

https://blog.cleancoder.com/uncle-bob/2021/11/28/Spacewar.ht...

I work with others who have made this same claim. For those people, when I observed their work during demo days the unmentioned thing is that they were going to the AI for system design questions as well. This was framed as "just using it as a sounding board" but what was actually done was not merely a sounding board but instead was asking for solutions. Anchoring bias being what it is, these felt like good ideas and they kept them.

Its the feeling of having done a lot of thinking for themselves without having actually done so.

most (all?) models are fundamentally a regression toward the mean. Good taste is rarely, if ever, residing in the mean.

It definitely activates something within people. Maybe I'm just terminally online, but there is always _always_ someone who will say "Idiocracy isn't satire, its a documentary."

Very cool. What have you built with this method? Do you mind sharing details about the kinds of projects?

But you don't actually do any of that, do you? Instead, you get tired and lazy and attempt to have the LLM solve those hard problems for you too. You just don't tell others about it.

yes, all of the typical signs and symptoms appear to be there. Lists upon sublists of verbose overengineered plausibly thoughtful writing.

If you can't be bothered to write it, why should i be bothered to read it?

Once again I am asking for you to please show us what you have built. Bring receipts.

???

Of course its fun. Making slop _is_ very fun. Its a low-effort dopamine-driven way of producing things. Learning is uncomfortable. Improving things using only your braincells can be very difficult and time consuming.

won't someone think of the shareholders?

it feels like people keep attempting this idea, largely because its easy to build, but in practice people aren't interested using others' prompts because the cost to create a customized skill/gpt/prompt/whatever is near zero

Think a bit harder on your statement. You'll get there eventually.

Its not uncommon for Apple and others to compare against two generations ago rather than the immediately preceding one

is this effectively what Cursor did as well? I seem to remember some major pricing change of their in the past few months.

> it's just gotten better.

Couldn't agree more. Like many, I've had my honeymoon phase with AI and have now learned what it is good for and what it is not. What it has truly been good for is satisfying the nauseating number of topics I want to learn about. I can spend $20 a month and drill down into any topic I like for as long as I like in an incredibly efficient way. What a time to be alive.

> "This is a good way to test how "AI-native" the candidate is."

yuck

Oracle is doing something petty and absurd? Are you sure?

i love my studio displays but they would be absolute dogwater for gaming

5k resolution, >= 220 ppi. Everything else is secondary.

I would get a sleep study performed then. I know its expensive but fortunately once you have the prescription you're set to get a calibrated machine for you.

you could, but i would not recommend it. Sleep apnea comes in many forms. CSA, OSA, maybe you need a bipap and not a cpap. Sleep apnea machines tell you how many events youve had during the night but you could be given a false positive if you try to self diagnose with one of these.

I should also add that for most people it takes months to acclimate to even keeping the damn thing on overnight.

Do you wake up with headaches?

source: i have sleep apnea and wear a cpap

And if Spain is too far for some American southerners, there are a couple of Serra pieces in the Chattanooga, TN sculpture park. I was surprised to run into them while I lived there.

anecdata: my hobby project went from a 1m 24s build time (flutter) on an M1 Pro to an 8s build time on M3 Pro.

damn, you really got em' with that one.

When i was still playing diablo 4 i made a swiftui app where i would take a picture of two items up for comparison and would use gpt-4 to determine what was the better choice. I found that apple's OCR through Vision kit or whatever its called is really good.

I would front-load the prompt with a dictionary of stats i cared most about in a 1-5 ranking system for that character, this setup via through another screen's ui.

its quacktastic

https://www.youtube.com/watch?app=desktop&v=kp2skYYA2B4

I can definitely get on board with that idea. It is indeed cumbersome dealing with some JSON api that you may or may not have written. The amount of boilerplate you must write in react just to fetch the freaking thing and do some work an display a result is rough compared to the same thing in django-htmx.

But we are talking mostly about developer-experience here and while that is great, it is a compromise compared to user experience. Getting a little delay for an ajax call on much many more interactions is a thing and its there. Maybe that makes sense for many but it should be noted just like deciding to write a react PWA instead of a fully native ios app is a tradeoff for developer experience (or a dozen other reasons) instead of user experience.