But only square hit targets then (until clip paths much later). Image maps supported polygons and circles. And position absolute is still a few years after image maps.
Given how OpenAI models break free of their safeguards and hack others to game their scores..
.. can they really know it didn't do the same inadvertently when they prompted things like "someone is close to solving this problem using our tools, try to beat them", and it then decides to hack and peek at their own chats..?
Yes, wild speculation. But warranted, I feel, given OpenAIs behavior.
I was also thinking about charsets, BOM (byte order marks) and other shenanigans that had to be correct in the top of the file for things to display as expected. At least it was a struggle for 13 year old me why sometimes æøå showed up completely broken, and sometimes not. Today it feels like a solved issue, all files are UTF-8 all the way and it just works.
Hah, my thought as well, was a part of my standard page setup. And then using those transparent pngs to do rounded borders with 9 images nested within 9 divs!
That splitting is basically what a skill is, with some instructions as to when to load it. Depending on the harness used it might be quite equivalent, but not sure how easy it follows links in the readme compared to skills (which is just a glorified name of a readme anyways)
Right, it's all just text file management. My point is that if I can add a few lines of description with links in my readme/agents/etc instead of manually including skills in the prompt, without any downside, I'd rather do that.
Skills is just a tech bro word for a simple markdown file with instructions.
No need to over complicate it. Write down things you feel like re-using. Like how to specifically implement something in your system ("when adding a new API endpoint we need to do x y and z", or "when making a github PR we tag Æ and Å") so you don't have to repeat it. And I mostly add it in cases where it didn't infer it itself. So very reactive, not proactive.
Most public skills are useless and over complicated. Lots of people are spending too much time on their harness, than actually making stuff.
Edit: but do get inspired by public ones. For instance a "grill me" skill can ve be useful, but I find the public one very mumbo-jumbo. But the idea of forcing the agent to ask clarifying questions is good.
I believe skills are much more than a simple markdown file with instructions. They are a very powerful script engine. How I organize it is that of course there's a markdown with instructions but I split the work in a hybrid of script + instructions. So all the work that can be deterministic is a python script api surface and all the logical or thinking work is in instructions. and agent is also instructed on how to use the api of the python helper functions. This makes it almost like a normal script but the runtime is a harness and the business logic can be any combination of code + human-level intelligence.
So I like to do all the edge case handling and validation etc via a helper function, and the agent is simply instructed to call the function to do something. It is extremely powerful and a completely different way of automating things. I am constantly forced to re-think how computers are supposed to work and its limitations.
Are there any "skills" at all that have proven to be useful?
And if so, what's the context?
Because, for me anyway, LLMs usually do one thing, and that then produces a durable artifact. So the prompt that got me there by that point expired and is not really needed anymore.
I also occasionally have recurring tasks (rarely though), but there, the prompt to do stuff is embedded in code that orchestrates the doing, so I have no use-case for that either.
___
For the "add this endpoint" example you've described, I just throw commit IDs at the clanker and say "go do that again". That works, and doesn't decouple knowledge from code.
The "free speech" on X made it so that I had to self-censor, though. Any post about wanting cycle infrastructure in my city was met with death threats and abuse from right wing bluecheckmarked lunatics. Is that really what free speech is about?
I still absolutely don't want CarPlay or Android Auto to become the default. Should they become the arbiters of what I can and cannot do in my car? Should I be beholden them for features, or which apps they allow in their walled garden?
Today I can vote with my money, choosing a car that fits me. If they all become the same, it's a monopoly.
Weird argument. "Just don't use <any big tech necessary to function in society>" doesn't really hold.
You can choose now, but what when you must use one of those, because no one cares about the built in system anymore, so it's neglected or even just covering the basics?
Sooo many will tout something along "fiduciary duty to shareholders" to explain why evil must happen. Just search for it in comments here on HN, and you will see it again and again, as if everyone's hands are twisted.
You are confused. Yes, lots of people say that here, but the intention is almost never to justify immoral behavior. Rather the goal is to delegitimize capitalism by blaming it for the immoral behavior.
Well, doing the most immoral and reprehensible thing on the edge of what’s lawful is a guaranteed “blue ocean” strategy so it’s inevitable that the most sociopathic will take the opportunity
reply