gingersnap

Greetings professor Falken

Most positive impact of AI yet

No, its not. Your logic is as reasonable as "60% of the time, it works every time"

Is the local model similar to model2vec?

I start to see a lot of these re-writes that depend on tests to state that its working. But the things that make software like Postgres and SQLite reliable are not mostly the test, but the real world production scars. That's where the reliability comes from, years and years of running in production.

I think this is the way. Not control, but just make it simpler for parents to handle their childrens devices. You dont have to make everyone share their age, you just make it so that parents can in a simpler way choose what the children should be able to access. Make it easy to do right, dont add more control. Its kind of the old anti-piracy copyprotections. The pirates always cracked it, and in the end, the ones who got to sit there trying to figure out what is the word in the manual is the user who actually paid for the game. So making it worse for the ones who paid, and better for the cracked version. So, make it simple.

I'm thinking that I gonna start making all my webpages <1mb in size, and compensate that with adding windows 95 to each page load.

I was hoping for this too, but when I saw that Eric Migicovsky went back to building pebble I lost my hope for it

My instinct is to say that I don't want the session as part of the commit. For me that is like a Slack thread discussing the new feature, and that is not something I would commit. I think that the split shouldn't be "is this done with a machine"=> commit, I think the split for AI should be the same as before. Is it code or changes of code, then it should be included. Is it discussing, going back and forth, that is not commited now. On the other hand, if you do a plan that is then implemented, I actually do think it makes sense to save the plan, either as commit, or if you save that back to the issue.

Still faster than most websites

But I actually think that one if the bigger arguments for single language models is the ability to have more languages. Im from Sweden, so I would like to have swedish on extremly high level, but I wouldnt like to have all other small languages on that level beacuse it would inflate the size. So, I actually think having multiple single language models, make it wider and deeper

Yes, I see the same thing. My working thesis is that if I can keep the codebase modular and clear seperations, so I keep the entire context, while claude code only need to focus on one module at a time, I can keep up the speed and quality. But if I try and give it tasks that cover the entire codebase it will have issues, no matter how you manage context and give directions. And again, this is not suprising, humans do the same, they need to break the task apart into smaller piecers. Have you found the same?