koinedad

I generally agree. If I build something bigger with smaller AI generated pieces I still built that thing, but even that thing doesn’t feel the same. I’m not as connected to the components that’s for sure. There’s a loss that is occurring

Maybe we should start writing code like the LLM will maintain it. I’d be curious if there are weird optimizations that the LLM can drive that might not be things that help us humans like DRY etc.

Edit: this small things drive me crazy when I’m coding with LLM… which is basically all the time these days, but I also read all the code as well.

I think this is cool and helpful but my biggest complaint is the writing style and word choice just scream LLM

This is pretty exciting. I hope it works.

Yes

Yeah it doesn’t really make sense. Very wordy and doesn’t really clearly explain the types of accounts. Those should be the first thing you layout.

If you’re aim is kids you probably want to start with a story about something they can relate to and how the different types of accounts help. The reading level feels like it’s targeting college+ but not clearly.

A checking account is this. This is what is helpful for, this is its down side. Here’s a savings account here’s a high yield. Here’s an investment account etc.

Edit: love the idea though!

Interesting, I also noticed thinning

Nice…maybe will help some of the recent attacks

My minimax has liberal usage at $10 per month, if you’re not looking for some amazing model.

The hidden notch issue is a pretty big problem. I had to look for tools to shrink the width spacing just to survive, and it just looks bad

I use right command + HJKL with karabiner and use it way too much, typing on someone else’s keyboard really throws me off but it’s great for my daily usage

The scroll jacking drives me nuts

Really cool breakdown. You’ve got a full Tesla gaming rig now!

I run lsof a good amount. This is a great idea.

Pretty cool to see. But the UI of the visual animations has some weird re-re-rerender bug, at least on mobile safari.

Self review is #1

Yeah my least favorite key since the globe was added. Randomly opens emoji keyboard on me

Pretty wild, nice job

I have to say I wasn’t expecting this

If you can figure out how to actually make it sound unbiased on the front page and then route to both sides biased versions that would be something.

Sorry we stole all your src code that you labored over for hours and hours of your life. Here’s a few bucks for 6 months to help train our model even more.

I literally just started doing this yesterday. Sometimes the tabs I have open help and sometimes they don’t. Yesterday they didn’t.

The Apple Pay one drives me crazy

I’ve been doing something similar and thinking about this in the last 6 months or so. It’s pretty crazy.

Classic

I’ve thought about this many times, maybe with a custom telegram bot!

I love the idea. And would be interested in making a game for it as well.

This is very helpful for a team and even though it takes a little time it actually speeds things up in the long run. Using PR templates can help. A general description of the problem including a screenshot or video go a long way.

I remember when I was working at a startup and a new engineer merged his code and it totally broke the service. I asked him if he ran his code locally first and he stared at me speechless.

Running the code locally is the easiest way to eliminate a whole series of silly bugs.

Like mentioned in the article adding a test and then reverting your change to make sure the test fails is really important, especially with LLMs writing tests. They are great at making things look like they work but completely don’t.

The title makes it sound way worse than the 7 reported crashes listed in the article. I’d be interested to see a comparison with Waymo and other self driving technologies in the same area (assuming the exist).

My kids read tons of books. But we homeschool and actual books are the main course of our education.