bavell

Really hate this trend/style. Sucks that it's ossified into many AIs. Always makes me think of young preteens who just started texting/DMing. Grow up!

You are just describing a "meme", deeper than language.

https://en.wikipedia.org/wiki/Meme

CR removing comments removed the soul from the product :/

Was always fun reading the top comments on big episodes. Finding those few other ppl who noticed that one small thing at timestamp 14:30, dunking on the first episode of the latest garbage isekai... etc

Also running a few single node clusters - perfect balance for small orgs that don't need HA. Been running small clusters since ~2016 and loving it.

Same situation, 10+ yrs deep with my first client, project still chugging along while I tackle bigger fish.

Can't justify spending much time on it now but a DIY no/low code solution for them isn't a bad idea.

Sounds like a good way of tackling this - thanks for sharing!

Iirc abliteration (ablation?) can be done without "training" and is pretty quick. It finds the individual weights related to the concept you want to ablate, and modifies those weights to "deactivate" them. Precision brain surgery, to anthropomorphize.

Most minimum/recommended game specs reference mainstream gaming CPU/GPUs, and most gamers know the strength of their own hardware relative to mainstream components.

If you're a very casual/young/inexperienced gamer then sure, you might have trouble comparing your own system with the min specs.

Correlation is not causation.

I play all my steam games on Linux/proton, zero issues for years now.

> Current video games are designed around streamlining content. As a player, your job is to extract all content from an area before going to the next.

Wrong right from the outset. Some games are designed around content and "extraction". Many are not.

Has anyone said they actually want this? I wouldn't, especially for traditional folktales.

You basically replied to GP's eloquent and nuanced post with, "nah bro trust me, purple is actually blue!"

China has a demographic time-bomb about to go off in the next decade or two. We'll see if they can survive it.

Nah, if you have an important application this is very low cost for adding tons of insight into how your app is running.

It's fairly common for artists to release a single or two from an upcoming album. Some artists release more singles than they do albums.

IDK about "efficiently" but we've been able to run llms locally with AMD for 1.5-2 years now

Chroot jail?

> how do you accept/reject and rollback changes?

Git

Great read and insights! I learned a few things and found myself nodding along most of the article.

> I think OpenAI may have taken the medal for best available open weight model back from the Chinese AI labs.

IMO, the "I think..." bit could be ambiguous and read as, "In my opinion, OpenAI may have...".

I agree with you it's not a hard/bold endorsement but perhaps leading with the disclaimer that you're reserving final judgement could assuage these concerns.

Did you mean to type equality? As in, "everyone on equal footing"? Otherwise, I'm not sure how to parse your statement.

I mean, there's always torrents

I'd love to try this on my data set - what approach/tools/models did you use for fine-tuning?

There are a ton of ways to do this that haven't been tried yet.

Unfortunately, it was predictable given the other "choices"

> I've basically wasted the morning on Claude Code when I should've just been doing it all myself.

Welcome to the machine

https://www.youtube.com/watch?v=tBvAxSx0nAM&t=45s

I'm on the basic $20/mo sub and only ran into token cap limitations in the first few days of using Claude Code (now 2-3 weeks in) before I started being more aggressive about clearing the context. Long contexts will eat up tokens caps quickly when you are having extended back-and-forth conversations with the model. Otherwise, it's been effectively "unlimited" for my own use.

The genius bureaucrat probably did as much research as you did and came to the same conclusion.

Yes, incredible productivity gains from using a single language in frontend and backend.