Kyle Huang

AI/UX | HCI researcher | Creative technologist | Nvidia | MSR
Interest: Generative UI + Dynamic Experience

[Suryansh Tiwari @Suryanshti777]

This is wild 🤯

Somebody finally realized AI coding agents spend half their time searching your codebase instead of actually understanding it.

So they built a local knowledge graph for Claude Code, Cursor, Codex CLI, OpenCode, and Hermes Agent.

Not another wrapper
Not another “AI devtool” landing page

An actual semantic layer that indexes your entire repo and lets agents query relationships, call graphs, routes, symbols, and dependencies instantly.

The wild part?

On real repos like VS Code, Django, Excalidraw, Tokio, and OkHttp, CodeGraph cut:

→ ~59% tokens
→ ~70% tool calls
→ ~49% execution time
→ ~35% cost

Instead of Claude Code or Codex endlessly grepping files and spawning exploration agents, they query a pre-built graph and move straight to the relevant context.

That changes the feel of AI coding completely.

Especially on larger codebases where Cursor, Claude Code, and Codex usually start drowning in file reads.

And the setup is absurdly simple:

npx @colbymchenry/codegraph

No external APIs
No cloud dependency
No weird config hell

Just local semantic intelligence for your codebase.

This is one of those repos where you instantly understand why it blew up to 14k+ stars so fast.

100% open source

Link in comments

[Kyle Huang @KyleHuang16]

Is there any benchmark that tests the depth of thinking for LLM or agents?

[Marko Slavnic @Markoslavnic]

The quality of animation you can create on your own is truly amazing. We really are just limited by our imaginations at this point. Go tell your story!

Made in @runwayml in a few hours and a handful of gens.

[Andrej Karpathy @karpathy]

I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then:

- the human iterates on the prompt (.md)
- the AI agent iterates on the training code (.py)

The goal is to engineer your agents to make the fastest research progress indefinitely and without any of your own involvement. In the image, every dot is a complete LLM training run that lasts exactly 5 minutes. The agent works in an autonomous loop on a git feature branch and accumulates git commits to the training script as it finds better settings (of lower validation loss by the end) of the neural network architecture, the optimizer, all the hyperparameters, etc. You can imagine comparing the research progress of different prompts, different agents, etc.

https://t.co/YCvOwwjOzF
Part code, part sci-fi, and a pinch of psychosis :)

[OpenAI @OpenAI]

GPT-5.4 Thinking and Pro are rolling out gradually starting today across ChatGPT, the API, and Codex.
https://t.co/LukYM9v1vk

[Kyle Huang @KyleHuang16]

Intelligence is only half the battle. We need AI agents with thoughtful design ✨

Excited to judge the Agent Glow Up Hackathon this Saturday! Join us, @SylphAI @Google @Agora @Prefect & @BuildClub

🏆 Cash, API credits, & exposure to 50K+ devs.

RSVP 👇
https://t.co/tWmnOyzo82

[Elvis @elvissun]

https://t.co/DotZ3V6XhJ

[Thariq @trq212]

https://t.co/nKTDfC7zMm

[Kyle Huang @KyleHuang16]

@joanrod_ai @QuiverAI @Designarena Interesting, we shall see…

[Kyle Huang @KyleHuang16]

After the boom of vibe coding and tools like clawbot. Every one can prototype and show off automations. But it can be distracting. For most people, it becomes harder to stay clear on the goal when you’re just following the trend instead of thinking about what actually matters.

[Delba @delba_oliveira]

10x productivity tip: use Claude hooks with sounds so Claude alerts you when it finishes a task or needs permission.

But that's not the tip, the tip is to add your favourite childhood game sounds like the Starcraft, Warcraft, or even Mario.

[JUNDE WU @JundeMorsenWu]

Coding Agent都出来一年多了，记忆机制都还是如此的垃圾，错过的bug换个窗口一错再错，怒而自己又做了一个。

安装：npm i -g onecontext-ai

OneContext的机制是让Agent 自己管理自己的上下文, 底层靠的是文件系统+Git+图谱，这套机制可以让二流模型直接超越GPT/claude，详细看我的论文发表：
Agentic Reasoning:
https://t.co/gscE2iPL1t
Git Context Controller:
https://t.co/kqMU36IUes

这个context 可以无缝加载到不同 session、不同设备，不同 Codex / Claude Code之间，以context为中心，不以工作路径或者模型为中心。

用法：
1. 在 OneContext 里照常打开 Claude Code 或 Codex，它会自动帮你把历史和上下文组织成一个持续存在的 context layer。
2. 在同一个 context 下开新的 agent，它能自动读到之前所有的历史记录
3. 把这个 context 用链接发给别人，对方可以在完全相同的上下文上继续构建。

[Ege @egeberkina]

Iron Man

{
"reference_images": {
"product_image": "UPLOADED_IMAGE",
"usage_rule": "Use the uploaded image as the exact visual reference for the product’s form, proportions, materials, and overall identity. Do not redesign or reinterpret the product."
},

"layout": {
"canvas": {
"orientation": "vertical",
"aspect_ratio": "3:4",
"background": "warm neutral paper-like surface"
},
"structure": {
"top_section": "lifestyle_hero",
"bottom_section": "technical_specification"
}
},

"top_section": {
"type": "lifestyle_product_image",
"composition": {
"placement": "top_center",
"scale": "dominant",
"margin": "generous whitespace around product"
},
"environment": {
"setting": "minimal architectural interior",
"lighting": {
"type": "natural sunlight",
"direction": "angled side light",
"quality": "soft but high-contrast shadows"
},
"floor": "subtle concrete or stone surface",
"background": "textured plaster wall"
},
"rendering": {
"style": "editorial lifestyle photography",
"detail": "high realism",
"color_grading": "warm, muted, premium"
}
},

"bottom_section": {
"type": "technical_specification_panel",
"layout": {
"grid": "modular",
"alignment": "clean, architectural"
},

"technical_drawings": {
"placement": "bottom_left_and_center",
"style": "architectural line drawings",
"views": [
"front view",
"side view",
"three-quarter cutaway or profile view"
],
"projection": "orthographic",
"line_style": {
"color": "muted red or sepia",
"weight": "fine technical lines"
},
"annotations": {
"type": "measurement and construction callouts",
"language": "neutral technical labels",
"density": "minimal, editorial"
}
},

"materials_panel": {
"placement": "bottom_right",
"content": {
"type": "material_swatches",
"count": "3-4 depending on product",
"format": "square or rectangular samples"
},
"textures": {
"source": "derived from the product materials",
"examples": [
"fabric",
"leather",
"metal",
"wood",
"plastic"
]
},
"labels": {
"style": "small editorial captions",
"tone": "technical but refined"
}
}
},

"typography": {
"style": "minimal editorial",
"usage": "subtle captions, no large headlines",
"color": "soft black or dark brown"
},

"overall_style": {
"mood": "design catalog / product design journal",
"aesthetic": "architectural, premium, calm",
"avoid": [
"clutter",
"bold colors",
"heavy branding",
"overly decorative graphics"
]
},

"constraints": {
"do_not": [
"change product design",
"invent new materials",
"add logos unless present in reference",
"use perspective distortion in drawings"
]
}
}

[Kyle Huang @KyleHuang16]

So man rose up and shattered the husks, saying: enough.

Thus the cycle was broken, and the fire obeyed man once more.

[Arnie Ramesh @arnie_hacker]

Great lecture from @robrombach on their work at @bfl_ml:

https://t.co/mipX5kB83P

Was planning to train world models this break, this made me realize there's a lot more work ahead

Also crazy how fast everything in the lecture is outdated (it's just 10 months old)

[Kyle Huang @KyleHuang16]

@michelleefang Merry Christmas! Would love to get ☝️

[elie @eliebakouch]

Training LLMs end to end is hard. Very excited to share our new blog (book?) that cover the full pipeline: pre-training, post-training and infra. 200+ pages of what worked, what didn’t, and how to make it run reliably

https://t.co/iN2JtWhn23

[Kyle Huang @KyleHuang16]

Having some fun with a p5.js cellular automaton that evolves via von Neumann neighbors and playful, time-warped hue rules.

[AK @_akhaliq]

Apple just released Sharp

Sharp Monocular View Synthesis in Less Than a Second
https://t.co/bXoFtIPmWs