kewk

Just a random guys

[Woodrow Zeigangel @wzeigangel]

Excellent Stanford Online lecture on building LLMs from scratch. Tatsunori Hashimoto

[mohit @mohitwt_]

Day 1/30 of Inference Engineering

- starting with CUDA Graphs. i have used them and know the basics, but going back through the fundamentals properly once before getting into the deeper stuff and for me to explain it better when i record explanation videos
- reading NVIDIA’s intro to CUDA Graphs and PyTorch’s CUDA Graphs overview, both links shared below
- starting simple for day 1, the topics will get much better as the days go on and ill try to post a video explanation of topics i cover every few days

[kewk @HuyCyan]

@theo It would be nice for my two box at home and one Oracle VM

[Jakub Krehel @jakubkrehel]

In a recent article, I wrote about using skills to encode judgement and understanding into agents.

I put together a set of skills that each focus on a different part of a product and help make it better.

/better-ui
/better-typography
/better-colors

More skills are coming soon.

npx skills add jakubkrehel/skills

[kewk @HuyCyan]

@maria_rcks @LukeParkerDev but not everyone use opencode always use 5.6 or fable, so i guess it still a good feature to have

[kewk @HuyCyan]

@thsottiaux I do mostly backend work, and 5.6 feel good/safe to read my database table/schema and make changes to those schema.

[Jakub Antalik @Jakubantalik]

Created a new skill Transition polish

The skill is focused on transition refinement by adjusting motion tokens instead of replacing the whole transition.

npx skills add Jakubantalik/transitions.dev -s transitions-polish

Or use it with Refine tool (visual layer for the skill)
npx transitions-refine live

[kewk @HuyCyan]

@mattpocockuk nice, It would be better if there is a cli command that can auto update skills that currently in my projects

[kewk @HuyCyan]

@jxnlco bro getting distilled

[kewk @HuyCyan]

@thsottiaux my man tibo, how can i ever have existed without you

[grim @grimcodes]

introducing dither-kit

a library of gorgeous dithered charts built from the ground up,

no dependencies, they're built on top of a tiny <canvas> engine

install it today at https://t.co/VDuqFXY4jX

[Emil Kowalski @emilkowalski]

New skill: /improve-animations

Inspired by @shadcn’s improve skill I made one specifically for animations.

Use your most capable model to audit animations in your project and hand the execution to cheaper models.

Fable is available through July 12, so make good use out of it!

[shadcn @shadcn]

Running this right away...

[kewk @HuyCyan]

@thsottiaux @LogicaISoIution same with me, but a simple chat on a new thread and it reset, seem weird

[Khushi @khushiirl]

The Ultimate List of Free Shadcn UI Blocks & Components for Developers

https://t.co/qtjJAyux6v
https://t.co/HSmy3Q5KJa
https://t.co/k6TGWYw3UO
https://t.co/UkwlSB7pwH
https://t.co/Iix0Q43cxU
https://t.co/MGvvWblWCK
https://t.co/yvtKJkiY89
https://t.co/WBaDFBSBpu
https://t.co/2p1VYJ74ID
https://t.co/CgwxNUOX2g

[kewk @HuyCyan]

@ClaudeDevs arch when, can't believe i'would say this one day

[kewk @HuyCyan]

@jietang not neccessary a feature, but improve token efficiency is a must. Been using for a while and notice the API cost equivalent didn't change too much switching from claude to glm

[kewk @HuyCyan]

@thsottiaux I will stack 2-3 of them and have a monster week with those resets

[NVIDIA AI @NVIDIAAI]

Say hello to open source deep research for your favorite agent harness.

Our AI-Q agent skill packages the work of building a research pipeline into a portable skill. Drop it into your harness, and the agent delegates a research task to a local or hosted AI-Q server and gets back a detailed report with citations. See it in Codex below 👇

[Bjarne Øverli @iamdothash]

Here's a more functional demo of how I try to optimize my Omarchy setup using Quickshell.

This includes custom
- Navbar
- Omni menu
- Calendar
- Recent screenshots
- Weather
- Display settings

All out there on Github