Lo vengo diciendo...

Mfs will be

*taps the sign*

# The Biggest Problem With AI Nobody Talks About: You Can't Say What You Actually Mean You have a vision for your app. It lives in your head as a sprawling web of business logic, user personas, technical architecture, and long-term ambition. Then you open Opus(Claude) and type:

BEING EXTREMELY BUSY EVERYDAYS REALLY HELPS YOU TO BE MENTALLY STABLE.

Lately, whenever I open this app and see the latest tricks, and hacks, and notes, and workflows, and spec here and skill there, I can't help but think: All of this will be washed away by the models. Every Markdown file that's precious to you right now will be gone.

Gitesh Sarvaiya 🧑‍🚀 Amp Claude the quality of results is way better additionally, claude code is bounded to claude models, but amp is not. e.g. I love their oracle tool, which is a deep reasoning tool that uses non-claude models appropriate for the task

🤣

Más claro..

This guy is BEYOND CRACKED. Gemma 4 already on MLX, bro has uploaded all models with quantization. 125 models uploaded in last few hours 🤯 New mlx-vlm repo also supports turbo-quant, and rf-detr too (among other things) If you are a mac dev, you better be jumping at this.

🤣 Excelente

🤣😂

😂😂

JA q genialidad

NASA Artemis passing close to the Moon

I built a free tool that turns "make me a chatbot" into production-ready prompts. It scores your prompt, asks clarifying questions, then engineers the perfect instruction set. New: inspired by Andrej Karpathy's LLM Wiki — every prompt you save compiles into a persistent knowledge base

😂

JAJAJA q hdpppp

Education by gamification.