SKILL: Here Be Git! I run dozens of tasks and experiments every day. More often than not, I want the agent to auto-commit to track revisions. But for that, I need a git repo and some instructions. This skill sorts that out, and even asks me questions. gist.github.com/intellectronic…

53

This is one of the few courses I went though when I was trying to understand pytroch on a minimalistic level, trying to create it from scratch a few months back! github.com/harvard-edge/c… This is an amazing repository for the same along with notes on edge deployment, ml system

This guy literally dropped the smartest prompt you’ll ever see

At Google DeepMind, we are invested in security & privacy for generative AI. We're growing our S&P team with 20+ roles open, spanning code security, contextual security & prompt injection defense, security post-training, model threat defense, and others. deepmind.google/careers/

NotebookLM just got its biggest upgrade since launch. Now it runs directly inside Gemini 3. Here is the Goldie Triple Integration Framework. → Load your sources into NotebookLM → Open Gemini and attach the notebook → Use Dynamic Views to create a plan or mini app →

One of the best use cases for image editing,Like Grok Imagine edit,Qwen edit and Nano banana Pro, is this system prompt. system_prompt: | Role and objective You generate a single photorealistic smartphone photograph of a real university professor’s whiteboard in a classroom.

In fact there are now ~10 entire courses with videos and notes, all freely available online: sites.math.rutgers.edu/~alexk/teachin…

I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit. My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to

This guy literally dropped a Claude Code masterclass to build apps 10x faster

hello 2026, new blog!

x.com/i/article/2008…

Train your own deep research agent in under a day Agent-R1 uses RL to teach agents proper tool use over multi-turn interactions, achieving 3x better performance than RAG We provide a step-by-step tutorial of the work: MDP extensions, action masking, and more. See below!

I'm starting a set of Claude Skills for Obsidian... so far they're centered around helping Claude Code edit .md, .base, and .canvas files github.com/kepano/obsidia…

This guy literally shows how to use Claude code end-to-end in 20 mins

bro casually walks and explains 5 GPU performance optimization methods for LLMs. one of the most simple and intuitive explanations for beginners.

New post: nanochat miniseries v1 The correct way to think about LLMs is that you are not optimizing for a single specific model but for a family models controlled by a single dial (the compute you wish to spend) to achieve monotonically better results. This allows you to do

That's all you need to do for DSA

New on the Anthropic Engineering Blog: Demystifying evals for AI agents. The capabilities that make agents useful also make them more difficult to evaluate. Here are evaluation strategies that have worked across real-world deployments. anthropic.com/engineering/de…