🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Instead of AI slop, I'm doubling down on drawing silly stick figures in MS Paint for all my blog posts. It's more fun anyways

Many such cases

Write more blog posts

Does anyone know on what basis Cursor/Windsurf pick files to make changes? Do they provide the whole codebase as context? I assume they're smarter than that.

Just a processed a codebase into a graph database (ne04j). Its query language is kinda fun

this is great way to find new ruby/rails talks

There is no moat, the app layer is the moat.

implement difficult (but interesting) projects. stuff ~20% above your current ability it raises your ceiling for solving hard problems, it makes you learn new stuff, and it makes you very efficient at easier problems repeat over a long period of time x.com/MaxMynter/stat…

Silly self-correcting proompting it works though!

Over the past couple nights & weekends, I've been building an agentic, semantic search engine for codebases. This is a very pre-alpha preview of it searching the svelte codebase. Lmk if you'd like to try it!

Performing semantic search on ambiguous queries, before getting all the nodes. Turning out to be a proper RAG layer for codebases

Felt the AGI today. I automated the boring parts at work using Zed Agent mode and it required very minimal hand holding. 10/10 would recommend.

Implemented proper tool calling for LLM-based decision making and context retrieval.

I knew nothing about AI agents a month ago. Now I've built a code-search agent that can take decisions and retrieve context on its own. You can just do things.

Coding agents are cool but they all need to do semantic search on the codebase. ripgrep is not enough

"Adding a console.log to each function handling authentication" With semantic search: 11k tokens used Without semantic search: 25k tokens used MCP server coming in handy.