I've been using Matt Pocock's skills at home, and they seem pretty great. He makes a great case for them vs other skills in his videos. I don't remember the exact arguments, but basically they're designed to be called by the user instead of called automatically, and that makes them take less context merely because they exist.
I've also found that they tend to coerce the programmer into thinking about the end result, rather than try to push them out of that role. His grill skills are about making sure the actual requirements are known, and his prototype skill can help explore things that need to be experienced to make a hard decision on.
That sounds like what I see with Plex, too. It definitely doesn't get it when the intros are unique. And if there's something later that's the same each show (an explanation of the game show, etc) it'll target it as the intro instead.
ah i see, then they must use a similar process. i wonder how big streaming sites do it. underpaid global south workers who manually tag the intro for every episode, or do the files come pre-tagged by the production. maybe a mix of both.
I think this is almost a tautology, to the point that I'm surprised more people don't realize it.
If you ask the AI to do more work, it uses more tokens. If you do more of the work instead, fewer tokens are used.
I've been looking at Matt Pocock's skills recently, and they're very useful. But they use tokens. You can do that work yourself without the token usage, and just have the AI do the coding, or you can tell the AI to do everything and pay the cost.
And you can scale it down even further, and reduce the AI to a glorified code completion tool, and use way fewer tokens. But it's not going to speed up your work nearly as much.
For now, finding the right balance is important. In the future, I think things will eventually shift to the point that we just hand most of it to the AI and let it go without worrying about tokens.
I think some may think they're helping like that, but I'm sure there are quite a few who enjoy the feeling of being a notable figure in the community because they answer so many questions.
These people have always existed and gave bad answers, but now they can do it so much faster, and with so much less actual thinking.
I did that when I was younger and internet forums we're still a thing. The difference is that I had to do actual research, which often took me half an hour or more, to solve the problem for the asker. I got knowledge and "the feeling of being a notable figure" as you have said. The other side for the answer. I believe my answers were good.
The difference is that nowadays people can just skip the research part and copy-paste Llama. No value added.
>The difference is that nowadays people can just skip the research part and copy-paste Llama. No value added.
and why would the person doing that do that? if the person asking the question wanted to know what an llm thought, wouldn't they have just asked the llm for an instant response instead of having to wait for someone else to respond? i'm at a total loss of being able to understand the point. it's obviously different if the response is a bot posting just in case that needs to be explained to a bot.
Oh, there were absolutely people giving good answers. I'm just talking about the same kind of person who now just posts what an LLM says, rather than do any research.
A quick AI Google search and some fact-checking later, and yeah. At least as of 2 years ago, Thunderbird was getting 3x the contributions that Blender was.
It just goes to show you how badly managed Thunderbird is, since Blender is doing so much more with the money. I'm more and more disappointed with Mozilla all the time.
That's relevant to why it historically had bizarre UX issues, like ctrl+s being the shortcut to erase the scene and start a new one: it predated most of those conventions, and has its own UI tooling. It's also always been designed to use three mouse buttons, coming from the Unix world, which used to be problematic when not everyone had a mouse with a clicky scroll wheel.
It's come an absurdly long way since I first dabbled with it in the early 2000s, and has gone from a niche FOSS tool to something widely used in its field.
Nowadays, Blender is an example of masterful UX for a professional tool. Immediately responsive, information dense UI with keyboard shortcuts for absolutely everything. Actions are composable, like with vim: something like "ex5" will extrude five units on the x axis.
Right, but those are for simple tasks. Much like vi or emacs, the keybindings are esoteric and historical but so much of what makes the tools great is reliant on on said historical and esoteric behaviour that changing any of it becomes an exercises in futility
Indeed, our Windows 11 offline Steam box also needed to disable LG & Switch App in taskmanager, and set LG apps to manual start in Services.
Apparently the 3 applications have some sort of screen partitioning/sharing capabilities, but it is still unclear if the LG App was remote access or not.
So far, LG is earning a lot of justified bad press. Should have returned it when I had to turn off the screens power-save mode to get it to stop fading out randomly. =3
For extra security against these text-to-speech model zero-shot clones, you might also want to use made-up gibberish words for which the pronunciation can't be reliably inferred from the spelling
I've also found that they tend to coerce the programmer into thinking about the end result, rather than try to push them out of that role. His grill skills are about making sure the actual requirements are known, and his prototype skill can help explore things that need to be experienced to make a hard decision on.
reply