ahepp

have we tried adding "make no mistakes" to the humans' prompt?

What do you think about the prompt “The first 6 digits of pi are 3.1415”?

actual or perceived realtime / determinism requirements

> I don't see a reason to trust it any less than closed-hardware, closed-source solutions. I would trust a fully-open-source PIKVM more, however.

Isn't jetKVM software open source? I thought it had a public buildroot fork? Been a while since I checked, maybe something has changed.

> The accidental static bleeding from onboard hardware, coupling through satellite structures and radiating across frequencies nobody authorized.

> The numbers tell the story bluntly:

I wouldn't waste too much compute trying to parse it, lots of LLM tells in the article. Pangram puts it at 100% AI.

Doesn't the premise that there's something inferior about these AI solutions, imply that there is something superior about human intelligence and that there will continue to be some kind of useful work for humans to do?

Not the main point at all, but what was it? Pattern matching rule nestled deep in /lib/systemd/network? Some kind of mysterious netplan / NetworkManager compat layer?

You need the next token to begin the next decode. So if you can get what might be the next token in half the time, you can kick off the next decode before the true decode for this token has finished.

If the draft was wrong you can kill the speculative decode, and you haven’t lost anything except for idle time

It’s true we can’t show the user the token until we have the true decode finished, but we can launch more work internally before we’re certain

I was so optimistic about using LLMs for "write once, read many" English language documents, but the more I've used the tools, the more pessimistic I get.

More and more, I try to ask it for low prose responses because its writing just seems like such a low signal to noise ratio

I'm curious about why LLM writing fails. Particularly whether LLM writing is fundamentally flawed, or if it's just distinctive and since it often reflects low effort, that distinctive voice is associated with low quality.

I find its reliance on extremely consistent rhetorical patterns concerning. The fact that it always finds a way to talk about how "It's not the X, it's the Y Z" no matter what topic you feed it, makes me concerned that the tail is wagging the dog

>I wondered if you have tried running all of your own writings through it to verify that it thinks you are human. I was struck by Freddie deBoer's recent piece where he did this

Maybe I'm taking the "all" too literally here, but I read the article, and I'm not seeing anywhere the author ran a substantial portion of his corpus through Pangram to determine the false positive rate. That would be really interesting to see.

He does

* give an example of a piece of his writing that was, when ran in segments, flagged as generated (which he disputes)

* multiply the size of his corpus by pangram's published false positive rate and estimate that a few of his pieces would be flagged

* get the pangram model to label a piece "100% AI" when it only has 3 generated sentences

* demonstrate the ability to intentionally trigger a false positive

What kind of prompting are you using to get those results? Anything I have claude or codex write carries a ton of distinctive characteristics. Obsession with "bit-for-bit identical", "it's not the X it's the Y Z" and so on.

It's driving me nuts, I constantly have to prompt it to "explain in plain, simple English"

A bigger question I'm interested in is why do LLMs speak like that in the first place? Is that really what you get if you took the average of the English language? It would be difficult for me to believe that.

Is there something about tuning for desirable qualities that forces LLMs to have this voice?

I wonder if this is due to experience with reading technical documentation?

I think the second requires deeper concentration, but is still quite readable compared to the kind of low-content engagement / SEO stuff one read on the internet even before LLMs

The zero 2 (W) seems pretty great if you just want a cheap linux device.