wild_egg

Haven't the SQLite tests always been closed? Getting access to them is a major reason for financially supporting them

It only takes 20 minutes and $200 to hack a closed source one too though. LLMs are ludicrously good at using reverse engineering tools and having source available to inspect just makes it slightly more convenient.

That's exactly the message I got from the video

I hate the feeling of playing roulette with my account every time I use their tools.

Since they refuse to actually provide definitive rules or policies, I have fully moved off their models and actively encourage all the other devs I know to do the same.

In what way is a single writer tying you down? It's so much easier to work with and scales so much better than postgres connections

> you can write it as stored procedure in your favorite language

When did postgres add PL/Lisp support?

It only switches to charging API rates if some part of your prompt triggers their magic string detector. Lot of examples of that floating around where swapping "is" for "are" or whatever will magically allow the request against your subscription plan again.

I've had my agents using tmux for these use cases for a couple years now. What does TUI-use offer on top?

The Dumb Zone for Opus has always started at 80-100k tokens. The 1M token window just made the dumb zone bigger. Probably fine if the work isn't complicated but really I never want an Opus session to go much beyond 100k.

Does that apply to subagents?

I keep hearing OpenClaw runs on pi?

EDIT: confused by downvotes. In this thread people are saying it runs on top of `claude -p` and others saying it's on pi.

The `claude -p` option is allowed per https://x.com/i/status/2040207998807908432 so I really don't understand how they're enforcing this.

Don't have a GPU so tried the CPU option and got 0.6t/s on my old 2018 laptop using their llama.cpp fork.

Then found out they didn't implement AVX2 for their Q1_0_g128 CPU kernel. Added that and getting ~12t/s which isn't shabby for this old machine.

Cool model.

Virtual memory doesn't matter at all. It's virtual. You can take 2TB of address space, use 5MB of it, and nothing on the system cares.

Have a read through everything that's needed for a full uninstall: https://gist.github.com/banteg/1a539b88b3c8945cd71e4b958f319...

Minimalist alternative with no hooks or dependencies for the curious: https://github.com/wedow/ticket

I think we're a long ways from that.

But with that said, those who learn the underlying mechanisms will always be able to solve more problems than the folks who don't. When you know the lower pieces, your mental model tells you when and where the higher level pieces are likely to break. Legit superpower.

seems similar to a couple of simonw's recent tools?

https://simonwillison.net/2026/Feb/10/showboat-and-rodney/

Factories benefit from economies of scale that favour centralization.

I think smaller groups handling more complexity is on point. But that's because each group will build their own bespoke factory catered to their exact needs.

I very fully expect a mass proliferation of custom programs rather than standardizing on a common set that groans under the weight of being so general to support all use cases.

I miss the Unix philosophy

Zig also makes this trivial

I've never used a system with Wayland (been on i3 for ~15 years) but every time a project like this comes up, I have to wonder why Wayland is even a thing. So many hoops to jump through for things that should be simple.

Sure, X11 has warts but I can make it do basically anything I want. Wayland seems like it will always have too much friction to ever consider switching.

why give it root access to your life? i don't use these tools but it seems like you should never give anything that access. if a claw needs email, set up a google account just for it and forward relevant stuff to it. share your calendar with it. whatever, just don't let it "be" you.

access control, provisioning, and delegation have been solved for a very long time now.

Oh awesome. I wanted to use this last year but safari hadn't shipped support yet and I hit some problem with the polyfill.

Looks like safari shipped support in December though so now I can go nuts

> This analysis will be “necessarily case-by- case” because it will “depend on the circumstances, particularly how the AI tool operates and how it was used to create the final work.”

This seems the opposite of the cut and dry "cannot be copyrighted" stance I was replying to.

> The content you are looking for is currently unavailable.

The power of voice dictation for me is that I can get out every scrap of nuance and insight I can think of as unfiltered verbal diarrhea. Doing this gives me solidly an extra 9 in chance of getting good outputs.

Stream of consciousness typing for me is still slower and causes me to buffer and filter more and deliberately crafting a perfect prompt is far slower still.

LLMs are great at extracting the essence of unstructured inputs and voice lets me take best advantage of that.

Voice output, on the other hand, is completely useless unless perhaps it can play at 4x speed. But I need to be able to skim LLM output quickly and revisit important points repeatedly. Can't see why I'd ever want to serialize and slow that down.

Do you have a citation for that?

Aside from consistent auth, that's what all APIs have done for decades.

Only takes 2 minutes for an agent to sort out auth on other APIs so the consistent auth piece isn't much of a selling point either.

It's been a while but why is uring not helpful for larger buffers? I'd think the zero-copy I/O capabilities would make it more helpful for larger payloads, not less

Scenes from this book have been regularly coming to mind for almost 20 years now. No idea how it holds up for new readers today but it left quite an impact way back then.

> Google's discoverability problem isn't just an SEO issue; it's reshaping how builders have to think about distribution from day one.

bro.