0gs

just curious -- do yall dislike JS as developers, or as users? i agree this is really cool though

aha! got it

huh. i honestly never thought they were all that different. didn't the same guy coin them both to refer to the same thing?

i feel like the only way this post isn't depressing is if it's supposed to be funny

all it takes is a little faith!

why the LOC limit? just because?

yeah, this was my first thought -- it must have DMT in it. but surely Vice, the biggest and best of the erowid-aura-scrapers, would know this?

counterpoint: i am pretty sure i can do everything i want text-wise for the rest of my life with just the skills i make and a reliable harness.

agree the prompting style in OP is a little over the top tho lol

wow resetting everyone's usage meter is great. i was so close to finally hitting my weekly limit for once though

the collective em dash hallucination is so goofy, i hope it is at least fun for the folks plagued with it. the em dash is a normal thing people use, and DEFINITELY a thing that pre-AI grammar checks enforced! i generally use -- when i write (no idea where i got it from); google docs has converted this to — forever. like literally since V1.0, and i don't even think you can turn it off. feels super fun to get bonus points leaving my (totally technically incorrect) --s intact though

i particularly like the idea that "a GTM team" is an organic component of running a business which can be impersonated by a grip of agents, as opposed to a convention that developed as a result of needing to pay a bunch of humans too much money to strategically choose to fuck over customers or sellers in the course of handling each unpredictable product adoption development, lest a poor poor pitiful technostructure be ripped apart by making too little, or too much, money. why don't all these tokenmaxxing people focus on making something BETTER

depending on what exactly "scraper tech" (lol) is, i suspect you may need a different, less opinionated tool to do the work you need to do. that said, i bet if you paid for enterprise, these problems would magically disappear? ;)

... the problem is it is rude to LLMs? i think they can handle it.

how do you define "need?" by my estimation, there are more than 1000 software products in the world, so i do not think 1000 is anywhere near enough.

i suspect "well-rested-and-vested troll" -- perhaps the most generous assessment -- is in the mix too.

"Again, we are not doing this because we have good ideas for products. If we had good ideas for products, we would make an AI do those instead. As long as we don't have to think about our 'customers' (lol) as 'people' we're happy"

in terms of mental insanity as a legal defense, you should read his blog post about joining "Grab" in 2018, where he said that food delivery is going to replace restaurants (and food trucks for some reason) with everyone ordering food from each others' houses

i do not know why this is surprising to literally anyone. did we think the D2C shoes made of felt were still a smashing business success/going concern? or have we not fully memorized the narratives that procure funding for struggling companies in this climate?

You can't view the contents without joining, so here's the welcome message if you want to roast it. ---- This forum exists to chat about (and connect with others who use) agent skills to get more reliable, more interesting, or just more results from LLMs.

If you still do not know what (agent) skills are after reading that web page for the spec, that’s fine. Let’s see, how about:

Skills are role-oriented text prompts used by agent harnesses (like Claude Code, Gemini CLI, Cursor, VSCode and its many forklings, etc.) to improve the usefulness of large language models in specific, predictable ways … while still allowing for plenty of emergent serendipity, also known as “benevolent prompt injection” or BPI (it kind of actually is, you can look it up — well, not the acronym, that was more an aspect of the “truth joke”).

They really feel like cyborg superpowers for your wordflows — and if you still don’t believe it, and need proof, you’ll find some of that here, is the hope.

This forum facilitates 3 dimensions of skill discourse:

discussion (admittedly a wide dimension)

demonstration and

distribution

Distribution can be you copying someone’s markdown and putting it in a file you package up and “install” (quotes redundant for some harness situations, but not all).

Or you can upload/download zips.

Safety? PRESUME EVERY ZIP YOU DOWNLOAD FROM THIS FORUM IS A CHARISMATIC TRICK BOTNET FULL OF POISON GAS before you install or use it somewhere.

It is extremely easy to open and introspect any real skill zip’s contents and computer files can’t “do” poison gas. Just check their work and your own.

We do not, generally, have any interest in talking about harnesses themselves, much less advocating for one or the other. If it can use skills, great! It’s a great harness, we all agree. Focus on the skills themselves.

Feel free to explicitly declare a license for your work in your post. Otherwise, by posting skills or code here, you agree that your work defaults to the CC0 1.0 Universal Public Domain Dedication (the same license covering the site’s general text).

It will be common to post and read LLM-generated text on this site. However, when you write a post as yourself, you need to write it in your own human voice and words and typing. However you want to do it.

But even in a flashy promo post for your cool new skill, you are not allowed to post LLM text as, or intermixed with, your own.

It will be very obvious, and you will be banned if you do it.

Put more officially: Clearly differentiate with visual and context cues and clues when and why you are including skill-assisted generated content in a post, and otherwise write posts in your own real human voice. If you don’t consistently do these things, you will be banned.

If you have your agents post here … you will also be banned, and obviously the agents will too. They can read stuff, that’s fine. No agent posting.

Beyond that, be nice, don’t be rude, bring positive energy.

You are kind of expected to “steal” the free stuff so no worries on that, but always respect others’ rights, and try to attribute others’ work even if you are not strictly “required” to do so.

Do not post anything confidential or owned by your company or something.

Please, be reasonable.

This Discourse forum (group?) is for personal and public entertainment and experimental use only.

How much trouble are you looking to get into? I’ve never been able to ban anyone from a cool thing before; don’t threaten me with a good time.

i mean this has to be Mythos related, no? biiiig stretch?

Obsidian is exactly this, it just totally doesn't act like it. in fact, it is a bit fiddly to make it do this. but THIS is why Obsidian is so useful

giving partial credit to Rust, the language, for shipping production code because you "hate" the experience of agent-driven development so much is an amazing move. i didn't think we could push things forward so fast. i guess Rust is just that powerful

this is totally just the revenge of scrum, and i love it. hyperscrum

isn't it weird that there is no attribution to a human here? i mean, eventually, they have to dropkick sama and install GPT itself as king, right? EOQ seems as good a time as any

i see him brag about how long these astroturf joints are on bluesky. had been a while since i'd tried to actually scroll through one and it makes sense now: so much more space to spawn subscription promos. better offline indeed

i can't wait until people make normal websites for their software projects again.

you're saying qntm is NOT an influencer? what a miscalculation i have made

he's a smart guy bc his day job is PR for AI companies.

i'm sure your entitlement to 24/7 uptime of a single unchanging product version, no experiments/releases/new features etc., is clearly outlined in the ToS you agreed to. just sue them?