sqvaard

well, I always hated YAML. But I also always loved YAML. The reasons for hate - exactly those you'll find in all the top 10 search results for "I hate YAML". Reasons for love? Exactly those you'll find in the top 10 search results for "in defense of YAML" or "you use YAML wrong". YAML is old, with its last spec update being 1.2.2 which is 5 years old, and that's still basically just YAML 1.2 which is... 17 years old. Almost voting rights.

So, I decided to give YAML another chance. Took a stab at something more strict than StrictYAML, more performant than all common YAML sers/desers I was able to find, and still just a simple drop-in file, basically a single-function ser and single-function deser with some fluff for perf.

My only problem is, I'm the only human on Earth who knows about it or uses it. So I thought, maybe it's time to change that? :)

BTW comments and opinions welcome. It's just 0.1.0, so with more eyes on it I think that a lot of things can be still improved or streamlined there.

Most people, actually. Remember, friend - ~half of the population has two digits in their IQ, by definition.

If we aren't in that half, it's by sheer luck, and nothing else.

kudos. Precisely this. People are doing agentic design backwards very often: YOLO then cry. But, if first you write skills, specs, set up orchestration, architecture and flows, including review layer, discrimination layer and trajectory management layer, then you task the agents with creation of verifiable testing and static analysis rig, based on the golden samples of high-quality manually engineered code, and only then you tell then to write conformant code.

Agents (and LLMs) are inherently non-deterministic. In coding practice, this translates to garbage code in the long run. The solution is simple - make the process as deterministic, verifiable and rigid as possible. Suddenly, you get all the bonuses of agentic flows (insane initial speed, trivial cost, express iterations etc.) with none of the usual problems... and suddenly, humans have hard time matching the quality of the final artifact with hand-written code, because we suck at testing, fuzzing and debugging - because we're basically single-threaded and overfocused. Agents, OTOH, excel at it, and context management is also trivial compared to humans.

can I be frank? It's a pile of rust. Nowhere near Muse 1.3, weaker than Ling 3.1, probably just a bit over Nemotron 3.0 Ultra, and that's it. Totally underwhelming - broken prompt responses, garbled repo state, derailed trajectories, hallunies, you name it. Maybe good for some trivial stuff, but that's it. Terribly slow on top of that, quite pricey after the free trial ends, not suitable for local use, and not good enough for cloud. We already have stronger free models, we have faster models, smarter models, cheaper models... Also, benchmarks are obviously benchmaxxed. Once again - on high effort it feels basically just a notch above Nemo. Get a real task, launch it, and cry in terror.

AND I'm not even comparing it to the flagships - y'know we just got Muse Wonder literally hours ago?!

tl;dr underwhelming