Sublime

Thumbnail of www-x-com-burnedchris-status-1958480070500098497-0ea9ac4846c842a3

We need to talk about this tool… 87 images in 1.82s. That’s 40x faster than @vercel's next/og. https://t.co/WmLtB4ymTs

Christopher Burns

x.com

the best chrome devtools feature is that it shows how long each line took to run https://t.co/2Db7vGDtgO

Aiden Bai

x.com

Llama 3.3 70B at 275 tps and this pricing is so good. I'm moving all of my structured output queries to it now. https://t.co/Q1xdSK8ecb

Shayan

x.com

zod: 819ms fast zod: 404ms arktype: 16ms conclusion: just use arktype https://t.co/pdDDvmNDqW

ArkType

x.com

Just finished some benchmarks, I can confirm that Azure's GPT-3.5 endpoint is at least 3x faster than OpenAI's endpoint. I can't believe I'm saying this, but it's time to switch to Azure. Just updated my oss prompt eng & guardrails lib to support Azure: https://t.co/ErigYvZdTr https://t.co/GYWLlx3eaQ

David

x.com

made a media-player component with @shadcn /ui. includes 120 fps scrubbing, volume and loading indicators, hls support and more. https://t.co/EAcRFpOkRI

sadman x.com

tbd https://t.co/bXHUsHHcw2

Luke Shiels x.com

A GPT-4 level chatbot, available to use completely free, running at over 800 tokens per second on Groq. I'm genuinely mindblown by LlaMA 3. Try it with the link in the next tweet. https://t.co/kSnXqY9HFk

Rowan Cheung x.com

OMG the claude-instant model is FAST https://t.co/ov59pdh9pC

Tony Dinh 🎯x.com