Discover real AI creators shaping the future. Track their latest blogs, X posts, YouTube videos, WeChat Official Account posts, and GitHub commits — all in one place.
Activity on karpathy/jobs
karpathy commented on an issue in jobs
View on GitHubActivity on rasbt/LLMs-from-scratch
rasbt commented on an issue in LLMs-from-scratch
View on GitHubLike having a best mate that helps you out with your server
@levelsio what are the benefits of running claude code on a VPS? Persistence, safety, obsidian?
View quoted postThis basic stuff does sound complicated but it takes 5 minutes to set up After this part, running a VPS is cheap, safe and easy Especially with Claude Code running it, which you can ask to check if the server is safe and stuff like enable auto upgrades and auto reboot after upgrade
When I set up a new Hetzner VPS first thing I do install Tailscale and once I'm in via Tailscale lock down the firewall to only accept web traffic on HTTPS 443 for Cloudflare IPs and SSH 22 for Tailscale IP That way nobody can get in I know I keep repeating this but it should
View quoted postWhen I set up a new Hetzner VPS first thing I do install Tailscale and once I'm in via Tailscale lock down the firewall to only accept web traffic on HTTPS 443 for Cloudflare IPs and SSH 22 for Tailscale IP That way nobody can get in I know I keep repeating this but it should be basics of setting up a new VPS So basic IMHO it should be part of any VPS service to default install Tailscale and enable it so it's the only way to get in Why? A VPS server is just like your laptop or destop computer but now imagine if it's connected to the entire internet with 8 billion people that can access it and try hack it You want to only have it accessible to you And if you want to host a website on your VPS (like I do), you should only let Cloudflare access your VPS so it can stand in front and block any hack attempts Never expose a VPS to the world wide web which realistically is the world WILD web
@levelsio @nfcodes I created a redis instance on hetzner with public port open for few minutes and someone was running a cryptominer the next moment taking 50% CPU 💀 After that I always use @Tailscale 👌
View quoted postNew chapter for Agentic Engineering Patterns: I tried to distill key details of how coding agents work under the hood that are most useful to understand in order to use them effectively https://simonwillison.net/guides/agentic-engineering-patterns/how-coding-agents-work/
Agentic Engineering Patterns > As with any tool, understanding how coding agents work under the hood can help you make better decisions about how to apply them. A coding agent is a piece of software that acts as a harness for an LLM, extending that LLM with additional capabilities that are powered by invisible prompts and implemented as callable tools. Large Language Models At the heart of any coding agent is a Large Language Model, or LLM. These have names like GPT-5.4 or Claude Opus 4.6 or Gemini 3.1 Pro or Qwen3.5-35B-A3B. An LLM is a machine learning model that can complete a sentence of text. Give the model the phrase "the cat sat on the " and it will (almost certainly) suggest "mat" as the next word in the sentence. As these models get larger and train on increasing amounts of data, they can complete more complex sentences - like "a python function to download a file from a URL is def download_file(url): ". LLMs don't actually work directly with words - they work w...
claude code + obsidian in under 1 minute