im not saying using ai to build is wrong or anything. im saying if you dont know what ai is building, you might land in serious trouble at some point. if you are able to build something by articulating your problem well, that doesnt mean others can. others = new people in tech. overhyping is creating false hopes. everyone is a vibe coder these days. just be an intelligent vibe coder and know whats going on and you will succeed faster and better.
which good models can one run on a 64 gb mac mini m4 pro? just asking as im seeing a surge in people buying mac minis for running llms locally.
ive cancelled my chatgpt subscription many time. unfortunately, there is no other app that matches the ux of chatgpt app on phone, web and mac. thats the only reason i keep coming back. google can do better. dunno why they...
There are so many good open source models now but they are not mainstream. The only reason I think is because the messaging around open-source models is not strong enough to compete with closed-source models.
NyRAG (pronounced as knee-RAG) is a simple tool for building RAG applications by crawling websites or processing documents, then deploying to Vespa for hybrid search with an integrated chat UI. When a user asks a question, NyRAG performs a multi-stage retrieval...

when someone says RAG is dead https://t.co/UvXY6LbWzP

Support for local llm models with ollama, lm studio, vllm, etc has now been added to NyRAG in addition to openrouter for a truly local rag experience. check it out here: https://t.co/K2JfavHIpB and dont forget to star the repo :)...

Detecting AI generated images has never been easier https://t.co/SLoueXHM5I
Here are my predictions for AI world in 2026: