spike021

I just recently tried this exact thing with GPT in Codex for my Plus plan. It said it would keep an eye on usage and note down checkpoints, but it totally forgot to.

No mention of the GR Yaris, huh?

huge plus one. Also the Brewers got Kyle Harrison a ring.

scrolls fine for me in an iPhone.

we have one of those by our office and it's funny how every day it says sold out but there's never really anyone there.

one time we did walk up to it as a few unscrupulous looking guys were hanging out and we figured they're just waiting for a restock. I don't think those vending machines really do anything to prevent people from getting as much as they want.

that's interesting! when i was a child I could eat canned tuna as well but sadly no longer.

Fish sauce has yet to cause any issues for me as well. I even have a bottle that I use for myself when cooking Thai dishes.

I'm actually very curious about the process.

I'm allergic to fish (can't eat tuna, salmon, etc.) but I can eat food made with pretty much any type of bonito-based dashi I've ever tried.

Especially Japanese food like nabe, nikujaga, Aomori-style thick niboshi soup base ramen.

Never really understood it.

if yours even works. i went through four or five with varying issues. yellow light of death, blinking red light

I like how you break down each type by how the agent compares to human behavior.

Granted I don't know the specifics behind training LLMs but at the end of the day they are typically trained on data that originated from humans.

So in some ways it's better to try and understand their contributions to our work from that mindset than just saying they are computers/text generators.

One other disadvantage you didn't mention is it's difficult to get a visa that makes buying a home there worth it, for the average Joe.

Most regular people can only visit Japan for 3 months out of the year. Even if you buy a home you can't get a visa just for that.

Maybe in your case the visa thing isn't an issue because of your wife but that won't be the case for most people.

how is there zero supply risk? claude will still package dependencies into a homemade solution at some level...

I remember riding in one in SF and while it was at the curb about to merge into traffic it saw a bike coming from down the block on our side and patiently waited long enough for them to pass.

On the other hand, I've had times while walking my dog across the street or through my apartment driveway and waymo's don't really slow down and do more of a faster pass right by us than I'd prefer, especially because a dog, like a child, can be pretty unpredictable.

I've been spending a lot of time iterating on feature implementation plans with Claude (at work) and GPT (for personal projects).

I then make sure they write a lot of tests and that if functionality is changed or added/removed then tests are updated alongside.

Generally I try to review changes myself and ask it to explain the changes.

It's not perfect but I feel like the planning step being iterative isn't all too different from my old research -> think about implementation -> implement loop.

At that point, reviewing any code changes goes hand in hand with how I coded before LLMs.

The major difference is I usually have it make any changes for things I don't like.

I find a lot of the websites I shop at for certain things do "dropshipping". So the product page will say "X in stock!" or similar when in reality they're telling you the inventory at a shared warehouse or even the original manufacturer and once you actually submit your order, the product needs to be shipped first to the store you ordered from. Then they ship to you. But both legs can take an unknown amount of time.