Garbage In Garbage Out

But will the chat bot understand itself? It’s fun when you start questioning the LLM line by line about its own slop in the same session and it starts flagging all sorts of things it did wrong. Why didn’t it write it correctly in the first place? Or is the fix wrong? Who knows? People I guess. The model is fed on knowledge but whether it will activate in response to your prompt and be restored unadulterated is a coin toss.

100 kb from multiple mb is fucking huge and it absolutely makes a tangible difference to anyone firing up the website from mobile data. Do not underestimate the power of snappiness, and keep up the good work.

B-but I don’t have to?

holy fuck

It’s hard having two decades of experiences in a domain I suddenly find myself at odds with. Reading about others having the same qualm reassures me that I’m not going crazy. On the other I feel drawn further into an untenable contradictory position.

Once in a while I give in. It’s typically when I’m faced with a non trivial problem I realize will take me days of learning before I have any chance of tackling it. My colleagues start suggesting it or share some slop to “help out”. So I think fuck it I’ll study later for now AI will solve it I need this ticket closed asap. I fire up a “decent” paid model and I start feeding it context. Every time it’s a nightmare. Hours of trying stuff that doesn’t stick, of questioning, of arguing with a chat bot, of wading through “here are the facts” and “good catch” and “I owe you an apology”. It’s not a shortcut it’s a fucking dead end. Then the bitter aftertaste can only be cleansed with cold hard time consuming actual learning.

That’s good to know, I’ve entirely missed the PS2/PS3 gaming era.

Tell me about how you upgrade your console’s hardware to make it last another five years. Tell me about how you installed an open source operating system to do whatever you want with your console.

Once you go through the hassle of setting up a Navidrome server the choice of music player really opens up. On my desktop I’m still going back and forth between Supersonic and Psyonic. I love both. On my phone I bought Symfonium and I’m really happy with it. It’s so easy now to pick some music to carry along.

Relevant XKCD

It takes a while to complete a first run especially if you’re not especially skilled. I’m a forty something that always had shit coordination and I managed to complete runs after a while. My advice would be not to obsess too much on that and enjoy the various side stories unfolding between runs.

What Baikal stuff? The thing’s dead and gone.

Imagine the unfathomable power of a company who would harness the velocity of rapid AI advancement or somesuch AND keep their employees. The world isn’t ready for such raw productivity. It would be too easy to get ahead of competition. Understandably they steer clear of such lawless behaviour. Gentlemanly sportsmanship, truly.

bro it’s volunteers all the way down

Hey, good to know Apple’s music has been DRM free for a while! I’ve bounced off iTunes many, many years ago.

Look. We already have a little computer in our pocket. Besides Apple can go fly a kite with their DRM audio files. Just let me own my phone.

EDIT: iTunes used to sell DRM music a long time ago and then I stopped paying attention. They’re DRM free now, my bad.

Friendly reminder that Google is making moves this year to make installing apps away from their store as painful as possible.

I’ve used Mint for a while and then I started getting curious about all these sexy Arch setups. I was intimidated with the install process though, so I tried out CachyOS and Endeavour. I ended up staying with the latter. It’s got that bleeding edge Arch flavour while easing you into it. I prefer Endeavour’s approach (we’ll help you learn) to CachyOS’s one (it just works).

This would be meaningful if the findings were not produced by the corp trying to sell you the product being hyped. Big tech has a history of “faking it till you make it” and I can’t help but doubt that this is really just Claude Code mostly autonomously finding issues.

Kessler called it in 1978