IceDane

.. what? There are like hundreds of these and similar apps.

I copy-pasted that question straight into claude and it answered without issue.

Protip: if none of your system can really be released independently, you're working on one system and should have one repo. Then you dont need a third release repo to orchestrate the release dance. You have a typescript/ruby monorepo without issues.

If I'm to explain what needs to change, that will by definition address processes or lack thereof that led to the problem, no? Which is then explaining what happened and why in an indirect manner, so many of the proposed changes may not make sense without more context.

There's no convergence, but there sure as hell is a lot of pseudo-scientific voodoo and overengineering going on.

The worst part about this is someone still using poetry for python development.

Love how there's an extremely lengthy explanation of the oldest way to track people on the internet like this shit hasn't been happening since cookies were created.

It's Victor Taelin?! Ye gods!

Why is everybody treating this person like some celebrity. Am I weird for having never heard about this guy?

Just like every demo is some pathetic one shot trash game that nobody would play, or something equally inane.

Lots of really silly people love to compare LLMs to compilers. "You don't look at the compiled code either" and "Back in the day, people also had negative reactions to compilers and wanted to keep writing assembly by hand" and other such nonsense.

Yes.. this happened recently. I basically always use auto mode, and when I asked it why it kept editing code with python, it explained that this is part of its prompt when auto mode is turned on.

I can only assume that's because their safety verification model is better at such snippets or something, but it means that the whole write tool they have which actually shows you the changes as they happen is just unused and it makes it more annoying to follow along.

I was just talking about this the other day.

When would I want autonomous driving? For longer trips. Where do those happen? On the motorway where driving is mostly straight and simple.

When on the motorway, my Tesla's lane assist gives me basically all the benefits on the motorway I'd get from full self driving. FSD doesn't let me stop watching traffic or release the wheel, and I'd still have to take over to adjust to traffic conditions.. i.e. the same exact thing I'm doing with lane assist.

I'm not interested until I can literally sit in the back and take a nap.

The developer is great. The game isn't.

I just chose to use an editor whose very architecture doesn't require nonsense like this so the editor doesn't freeze on me.

That sounds cool, but it's either a handcrafted world (if NMS has those) or pure luck. If it's the latter, then it can't have any depth. At best it can have some procedurally generated content that's going to be something you've seen before. Looks cool, but no substance.

It's been years since I last played it, but when I did I finally did so for a while until I finally found myself at a space station with other players and whatnot. And some random dude just gives me something like tens and tens of millions in cash. And my friend. And a bunch of other people in the same station.

At that point I was still rather new to the game. I had little money, few resources, understood little - which was the whole game for me. Discovering new stuff and trying to make money. And being given all that money sort of just .. ruined the game for me. What was left was the very meh storyline and maybe exploration, neither of which had any appeal to me.

I've not had disputes worth that much in nearly 40 years on this earth. Makes me wonder whether this is just some exaggerated nonsense. The article is certainly written by an LLM.

I was forced to work with IBM closely for years. That has led me to believe it's the single most institutionally incompetent company in the world. If they ever do anything well it's pure coincidence and most likely due to some single hero dev.

I don't see how this can be so difficult to understand. If the second word in my first sentence were misspelled, does that make every other word or letter that comes after wrong?

Sure. And I'm sure that their users will take kindly to being banned with prejudice and without recourse. By adopting this policy they are committing to policing it and acting as judges. And at some point someone will be banned that shouldn't have and it will go on social media and so on and so forth.

They'll also have a fun time drawing the line. What if someone uses agents to generate boilerplate like tests? Are a few files out of hundreds enough for a ban? If not, are they going to force users to write the code manually? How are they going to verify that?

It's a big can of worms.

Well, that's their prerogative, I guess. But the burden of proof will be on them, of course. They can't expect users to prove a negative. There are simple tells that would reveal a lot of projects. Claude Code's moronic defaults of littering commit messages with both a CC author trailer as well as a session link will reveal some, but those are easy to disable. Then there is stuff like prolific comments, em-dashes in comments, etc.. but none of those are real proof that a project was built with agents.

Either way, I was never interested in codeberg and this just means that I'm less interested.

I think if you're suggesting that Steve Yegge somehow invented having agents collaborate, you're way off base. People started talking about agents collaborating very, very early on, and people have been doing experiments like this for ages. There have been libraries to build e.g. graph-based (possibly multi-agent) workflows from the early days, before even structured output was a standard thing in the APIs.

The only thing Yegge did was come up with really stupid, convoluted and anthropomorphized language to describe the process and then write unhinged articles about it

Also famously terrible. If not for the walled garden and the fact that anthropic can take away our ability to use custom harnesses any day, I would not be using CC. Given some of the features they add I've also started to suspect that their models are making product decisions. Not necessarily intentionally, but more in the sense that I think their engineers just let their models build and add whatever it feels like is a good idea to the codebase and then they just publish that.

Everything Steve yegge has done has been trash. That's why nobody is talking about beads or gas town. It was clear even in the beginning that it was a borderline AI-psychosis-fueled trash fire.

There's a good way and a bad way to use tools. My suggestions were based on my extensive usage of the tools in question.

It has to be both. You can lay things out in memory so they are tightly packed together and thus ostensibly cache efficient but that doesn't help you if you index into that data structure in such a way that every new index loads a new cache line.

Stop using compaction. Stop treating sessions as something you keep alive for weeks. Set up a proper workflow for handing off work and start handing off well before maximum context is hit. It's less efficient, slower and more costly to constantly be sitting at high context and compaction is just not good.

But push is not for use in production? It's for development. You generate a single custom migration that sets strict, apply it, and then you can use push as you want (during development, not for deploying actual changes to your database)

It's really weird to me how the SQLite author is clearly a very smart guy and talented developer and then his argument against type safety effectively just boils down to

> But I do not recall a single instance where the bugs might have been caught by a rigid type system.

Which is a shame. Of course the author writes more than this, but this is IMO largely the gist of the argument. At this point it's beginning to feel like this is mostly a sort of stubborn sunken cost fallacy, where they've been arguing this for so long they can't take the "hit" of agreeing to change the defaults.

But only just. It doesn't really replace graph databases. It's mostly a slightly more convenient ways to write certain kinds of queries, but it doesn't come with anything else you might expect from a graph database.