amorroxic

Curious on what backs this assertion. As a counterpoint we’ve been running 200+ models in production for more than 5 years - language models, embedding, classifiers, low tens to hundred M params. Traffic in the order of 1-2M requests/day and everything is enabled by onnx with some cgo (or Rust) plumbing on top. What’s your SLA?

Thanks a lot for this. Also one question in case anyone could shed a bit of light: my understanding is that setting temperature=0, top_p=1 would cause deterministic output (identical output given identical input). For sure it won’t prevent factually wrong replies/hallucination, only maintains generation consistency (eq. classification tasks). Is this universally correct or is it dependent on model used? (or downright wrong understanding of course?)

A real-time video processor in hardware:

- static (mp4) or live (hdmi) input, hdmi output

- a collection of effects (various distortions, color glitches, demoscene-like) applied over incoming video stream, maximum of 4 effects stackable on top of one another

- midi controllers support (controlling actions/params of effects via CC)

- modulation of effects params via LFO and audio events (bpm, kick, tonal detection)

- loading of .glsl shaders (eq. shadertoy.com)

- dynamic input resolution, output either 360p (rpi 4/5) or upscaled to 720p / 1080p (networks like SRGAN over Hailo / RPI or RK3588 with a Radxa 5B SBC).

Given a 2nd screen (timeline editor) would love to evolve this to something like a hardware editor, somewhat in the line of DAWs in the audio world. Most things are working with biggest challenge now being building a control surface (buttons, rotaries + associated oleds, etc) and attempting laying it all on a PCB, a process I don't know much about. If there's interest welcome comments and could elaborate more.

first $100: pdf photography courses with weekly chapters

first $1000+: built a shop selling silk scarves (100-odd) I collected myself from Laos/Cambodia/Thailand to balance trip budget (25yo back then, mad travelling). Sold all scarves, closed shop.

the null concept being referred to as “the billion dollars mistake” - until discovering optionals and gradually opening up to FP, category theory, etc

This. Same scenario here, fondly remember 1080ti, that was the workhorse for us alongside cloud training (startup with ~100 nlp prod models, ner, siamese, count models, etc). ULMFiT and language transfer was the moment when upgrades felt necessary though 2080ti’s vram unfortunately stayed the same (never had access to Titans for instance so perspective may be limited).

and unfortunately social makes it possible for one to yell “Fire” in all crowded places at the same time.

it’s still there unfortunately, no close button either.

Signed it too :) Can’t remember a particular reason though in our case (former cofounder) we were discovering the actor model, immutability, streams,.. tbh remember a great deal of fun programming during those days, insane schedules and whatnot. Though truth be told our most productive systems are Go these days (sold, stack still holding).

Three strikes and you’re banned forever, better choose the moment well.

Thank you for the perspective here. A wish there was a way to bookmark comments on HN..