I do think it pays to be nice to the model. When the context window is running out I like to ask "please summarize what went well and what didn't work in this session. How could the user be more helpful?"

>I do think it pays to be nice to the model.

there was something on HN a few weeks ago about how most/all models perform better the more rude you are to them.

(i still say "please", i can't help it)

that article seems to suggest 20TB total over the dozen deployments in prod.

Ok im supposed to assume that a model doesn’t know cars get washed at a car wash?

But then im supposed to give it access to write code in my repositories. Sorry, what are you trying to get at here?

There's meaning in the term "car wash" that it understands. But I don't suspect anyone has taught it that for 99.9% of people, going to car wash ONLY means that you're going to wash your car and that it should make that implicit assumption.

What if you're the car wash owner? Or a maintenance technician? Pretty easy to just walk over there if you're just 50ft away.

to your point, when my Aussie friends first mentioned a "car park" to my north american born self, i wondered _momentarily_ what that was, then realized it's sort of a fun name for what i would call a parking lot.

I've never thought of it as a fun term before.

We use "park" as "I will park the car" not park as in "amusement park"

Why isn’t the “pantry” called the “food store”?

Does your pantry have a cashier and let you buy stuff there?

Because a food store sounds like it does.

yeah but syntactically "car park" gets used like a noun phrase, not verb phrase, which was (to your point really) what had me think "huh?" momentarily.

Every model knows what a car wash is.

If it doesn't, what's the point using it? Trusting it with your workflows, your code?

When I was about 4 years old, this was the first movie I saw in a theater, it was a double feature with fantasia. Next time I remember going to a theater when my parents took me and a friend out of kindergarten to see Star Wars on opening day.

isn't sound a time series? I guess it's not usually 64-bit doubles.

Yes it is. The mismatch is mainly representation and purpose: audio is usually int16/int24/float32 PCM, and audio codecs often exploit perceptual loss. fc is lossless and currently tuned for float64 streams.

is that no longer true?

No, now you have the option of using CAP_NET_BIND_SERVICE

There is also net.ipv4.ip_unprivileged_port_start

If the application supports it, there’s also systemd socket activation (or traditional inetd sorta stuff too if that fits)

Forgot to mention: you can use systemd-socket-proxyd to bridge to an application that doesn't support socket activation too: https://www.man7.org/linux/man-pages/man8/systemd-socket-pro...

I don't think it has had a BSD license this century, Sleepy Cat was selling licenses in the 90s before Oracle bought them.

I wholeheartedly agree with these, and I think point 1 is a real danger.

An ai system can't lie, and it can't deliberately ignore your directions. The current frontier class does not have a model of the world or their action -- they live in a world of words. Scolding them or arguing with them has no point other than to scramble the context window.

I do think zoomorphizing them might be useful. These poor little buggers, living as ghosts in the machine, are pretty confused sometimes, but their motives are purely autoregressive.

It's who the dead heads follow around now.

As well as Billy Strings, Goose, King Gizzard & the Lizard Wizard, Sturgill Simpson, John Mayer…big scene these days

I agree that anthropomorphizing is a real risk with LLMs, but what about zoomorphizing? Can feel bad for LLMs without attributing them human emotions/motivations/reasoning?

In the same way you could feel bad for a pokemon I guess.