bythreads

built one in 1836 just before the war started

I’m confused this seems exactly like a skinned glm 5.3 - flash with a few context injection tricks and guardrails - whats going on with these “startups”?

half of them died of diseases brought by the spanish...

i think this is a wash at best, but might be ok if you have a very specific model that is completely unoptimized - but these days you could just point your astra level llm at it and say "make this faster"

Ok so i took the time to benchmark this on the following on my m5 max 128gb:

Qwen3-4B-Instruct-2507-4bit Qwen3.5-35B-A3B-4bit Qwen3.5-9B-MLX-4bit Qwen3-Reranker-0.6B-4bit Qwen3-Coder-30B-A3B-Instruct-4bit qwen2.5:0.5b

and the results are what i kinda expected to begin with, this adds next to nothing? - also the repo was pivoted from a playwright sub assembly to this not long ago - so my conclusion - THIS MIGHT be worth some watching if you have a model where no-one!, has optimized it at all - and where it does not use anything native to your platform.

results (averages)

VIA rapid-mlx :8902 (MLX) Decode: 175 tok/s TTFT: 64 ms prefill (~760 tok cold): 594 ms

Magnitude 0.2.1 (GGUF/llama.cpp+Rust) Decode: 161 tok/s TTFT: 111 ms prefill (~760 tok cold): 669 ms

Nah llm optimizes for the middle of the bell curve - most designers and designs are meh so they’ll output meh across the board . Takes rare skill to do it right

Thinking gucci is gucci

Sorry, isnt this just compression? Lookups burn tokens just on the other end?

Any drinks list without a pan galactic gargle blaster is sus

I’d do the same for a11y an internationalization purposes - however this is juts a bad implementation of it from an americans perspective.

You’d change seperators and position if you truly wanted to do this right

Its basic date wrangling and tbh i see nothing malfeasant here

Its basically yyyy/mm/dd yy/M/d mm-dd-yyyy stuff but suuuuper lazily done

maaan i got had there

stone age gets a vote from me!