wild_egg

Aperture supports extensions? What sort are you working on?

> Depending on where you draw the line for millennials the school computers could have been running anything from Windows 95 to Windows XP.

Weird. I distinctly remember Commodore 64, DOS, and Windows 3.1 at school. Kind of hard to use Windows 95 before 1995, but I am pretty sure I had a Windows 98 SE machine at home when my school finally got Windows 95.

Why is BASIC a weird choice? It wasn't really a choice at all. All the computers in my school ran it until I was 8 or 9 and the school board could afford to upgrade to Windows machines.

Ask a color blind person to spell "red" and "green", then ask them how many red apples are on the table.

LLMs work on tokens. They literally cannot see individual letters. Yet, unlike humans, they can instantly create a tool to solve this task for them and never be stumped by it again.

I'm so tired of this brain-dead gotcha comment.

Last time I did anything with a BERT, you had to train or fine-tune. Is that not still true?

For me the cool bit is that it's all in-context learning or whatever so you can use it in any domain with zero setup.

Maybe bert and co. could do all the same things before, but the way in which you use them is quite different and that helps a lot.

Goes both ways.

https://terrybisson.com/theyre-made-out-of-meat-2/

What's the point of switching to switch? I've only ever used checkout and not sure what I am missing out on.

As an old person, what's the modern attitude?

It's a limit on input tokens. So that's 3 50k requests per minute. At Cerebras speeds, that's about 5 seconds of usage per minute.

I was very excited last year for their coding plan but seeing a burst of requests pulse and then sitting there watching the cooldown reset is really not a great time.

Even though each individual request was fast, the sessions were only maybe 10% faster on wall clock time since there was so much waiting time.

Don't all the major ones have free tiers now? Pretty sure you can do this direct from the Google results pages even

Moore's Law has nothing to do with processors getting faster. Dennard scaling stopped working but Moore just slowed somewhat, not stopped.

Wait, you actually found a viable counter to The Bitter Lesson? Please say more

Why are you talking about markdown? LLMs output bytes and llama.cpp has to process those bytes correctly. What if the LLM outputs a null byte and causes a buffer overflow somewhere and starts writing into executable memory?

Again, we are not talking about agents or your Python API script but instead talking about exploitable flaws within the inference engine itself. It wouldn't output `rm -rf`. It would output literal CPU instructions that llama.cpp would start executing directly. The payload would never get back to your Python script.

Article isn't about agents. It's about the inference engine itself being exploited by a malicious LLM output before it is ever sent to your machine or harness.

You should have just got a reset today at least. There are several sites around for tracking them now. I use this one:

https://codex-resets.com

> Emacs Lisp — millions of people run Lisp every day without knowing it, because their editor is a Lisp interpreter.

Are there seriously any emacs users who are completely unaware of elisp? Isn't elisp the entire point of picking emacs?

You're funny

Because the system allows for it. Lisp is a far more powerful language which enables faster iteration and development.

If you give that to an LLM, it is then also able to iterate and develop faster.

In this case, the better language buys you increased iteration speed in addition to performance, and that is worth a lot.

LLMs have been solid at writing Common Lisp since Sonnet 3.5 and have been near flawless since the Opus 4.5 release.

The niche language thing is really not a problem at all any more. If you're working in some esolang it doesn't take more than a 1-2k token primer in the context to get great results, and lisp is popular enough to not even need that.

The benefit of having the agent directly in the image like with Autolith here is that it can directly inspect all defined symbols and explore and orient itself automatically. Really doesn't need much guidance to get great results.

Ah ok. When I talk about fast I am usually referring to user perception rather than clock cycles spent. Users won't notice 1ms vs 10ms but will notice 100ms or 1000ms.

For me, it's a law of diminishing returns thing. I would (and have) hand roll assembly if I want actual speed.

But we are talking about personal software. Write once, run everywhere browser's exist with essentially no tooling or complexity or deployment concerns.

What does writing everything in rust get me instead that is worth the significant increase in effort and dev time and deployment?

View Transitions are your friend

Who said anything about cloud?

I run all my apps on my desktop and access them over tailscale. All web apps and I install on phones as PWAs. Super ergonomic.

As for this:

> Local software runs faster

What? Why? Is this some assumption about network requests?

None of my personal software ever has a loading spinner or lag. If it's designed well, each interaction should fit in a single TCP packet so network round trip is imperceptible.

If your web software is slow, that's a choice you've made. Plenty of slow local software around to balance the scales too.

EDIT: Using local files with a web stack is also easy these days. The only con of web software is lacking that native aspect. But native appearance is rare anyway these days with every company just shipping electron bloatware.

It still works exceptionally well in 2026 and generally creates better and faster experiences than an SPA with far, far less code.

You want client side table sorting?

It's really easy to do this with server rendered HTML. Put a link with the sort param in the column headers and be done.

Data point of 1 but I prefer all my personal software to be web based so I can easily access it from my phone, laptop, and desktop and not worry about syncing things or installing or updating when I switch devices. Also makes it trivial to extend access to family members as needed.

It's very rare that I reach for local software these days.

That is not at all how copyright works. If the encoding is irrelevant then virtually all code on GitHub is violating copyright as there are vanishingly small numbers of actually novel ideas.

As the sibling comment said, the existing precedent is for an entirely different scenario. If a human claims no involvement then it's fair to say they have no ownership. But if I meticulously guide an LLM to implement precisely the code I want to be written, that's an entirely different thing which has not been tested in court.

A similar concept: if I type the code via a brain-computer interface, does the interface get ownership because it is inferring my intent? If I type it via an LLM, why is that less legitimately my creation?

It's fine if I vibecode something and never look at or claim ownership of the code, but if I am actively involved in all of the code but it is written to disk by new tools instead of old tools, why is it suddenly not mine?

I'm sure we are going to have to wait for some actual court cases to establish precedent but I don't really see why this is the case.

If I use a fancy brush in Photoshop to paint flowers into a PNG — do I own the resulting image? Code is bytes of text on disk, not much different from bytes of pixel data in a BMP.

If I have to type every character by hand in order to own the bytes, then it would stand that I would have to input every pixel by hand in Paint to own a graphic. No? Even using the Fill tool is automating the creation of those bytes and would mean I don't own them. Right?

I have an intention for some bytes of data to be set. If I use an LLM to set them instead of my own fingers, why are the bytes suddenly not mine?

I do not understand.

Relative few that have been around a long time? There is a plethora of 10+ year old incrementals with virtually endless content at this point.