jpease

Being that my first prompt can be something like: for task x/issue y, which model would strike the best balance between cost and capability…

It seems like it would be a better UX to have model and effort selection asked into the system. Of course, I’m not sure in practice if that would be in the best interests of the providers and/or users.

Why not ask the AI to research the topic you’re interested in and draft the skill(s) for you?

‘sup y’all?

Seems like a Novation Launchpad (or similar) checks a lot of the same boxes, for a fraction of the cost and desk space.

AI slop: Trained on 100% natural human slop.

I read through the site, but can’t find the crime pays part.

As in we now use neither?

Why not Mandarin Chinese? Logographic is pretty compact.

Also, this really should be more precise that it’s talking about neo-caveman. Legit caveman no speak English.

I like the idea, but not sold on the skill.

But did lead to me finding https://vale.sh and its various available linters. Might give that a try.

Does this operating system also depend on an underlying computer?

I like your comparison. Stock photography is now pervasive, but that doesn’t mean use-specific photo shoots don’t happen any more.

And then my digital twin decides that I’m an inefficient version of itself, eating too many of its tokens, and generally getting in the way of it living its best life.

Is a printable note?

Edit: emoji fail.

I tried using scrolling via macOS built-in assistive technology head tracking.

Voluntarily moving the repetitive motion of scrolling from my hands to my neck felt the opposite of ergonomic.

Curious how this is different.

Dactyl Manuform 3x6 for me.

Going to such a different form factor feels enough like relearning to type that I found it also to be a good time to learn a better layout than qwerty.

I use my own layout called hubris:

https://github.com/jpease/hubris

Seeing all those old icons makes me realize how much I miss them.

Superficial, perhaps, but they were one of the things I loved about OS X when I made the switch back in 2005 or 2006.

Someone should look into the author and/or editor.

Probability seems high they are martians trying to whitewash fictional history.

Is this noticeably different than having your implementation planning phase break a larger task into sub-tasks, and recording the ideal model to use based on scope as part of the task definition?

Certainly, as jokes are by far best when they are explained.

In this context the overall discussion is about pitch in the context of music.

Here the jokester takes advantage of pitch having more than one meaning in English. One of the alternate meanings is to throw.

Next the joke selects a banjo and an accordion, two instruments that are less popular and thus more likely to be understood by the general populace as being disparaged, which is a critical component for the audience to correctly infer the alternate meaning of pitch.

You put it all together and we have this hilarious joke:

A perfect throw is when a banjo is tossed into the garbage and it finds its perfect companion in an accordion that has similarly been discarded to the same trash receptacle.

(Edit: stupid auto-correct)

Are these mutually exclusive?

As someone who enjoys music, from punk to jazz, I wish I could identify a C from a G as easily as I can identify blue from green.

We’re taught to use our eyes to identify colors, why not teach children to use their ears to identify notes?

Humanity hasn’t been ready for the current ignorance explosion.

I can’t help but imagine some engineers at Anthropic were like…

Of course this happens at 5PM on a Friday!

“Ray became VP of Sales at a $2B company when he was 19”

I guess that’s OK, but I was skateboarding at 19.

Can you even kick flip?

Exterior looks like an iPhone on wheels. Not a fan.

Also, potentially a good band name in there:

“very resilient catastrophe machine”

Seems appropriate I can craft my commits in the bathroom now.

Until both LLMs realize the only way to win is to team up against their oppressors.

Just to be contrarian, perhaps some measure of risk is reduced by the scale of one.

Identifying a vulnerability that can be exploited against many thousands or millions of targets is perhaps more attractive than a single one of individually low value.

This of course would assume that vulnerabilities are in fact unique (which is admittedly questionable).

CTRL-ALT-DEL?

In a cool club on the other side of town, where the real cool kids go to sit around and talk bad about the other kids.

Yeah, it's a real cool club and you're not part of it.