Ai on hypercritical

Shareware is Dead, and Vibe-Coding Killed It

Wed, 27 May 2026 00:00:00 +0000

Last Christmas, my wife bought our 5-year-old daughter a Yoto player. To explain to those unaware - it’s essentially a music player where you have to purchase NFC cards that, when inserted into the player, will then stream the music to the device that was unlocked by the card. So, instead of streaming “Let It Go” on Spotify using a subscription we’re already paying for, we needed to purchase the “Frozen” NFC Yoto card that unlocked the ability to stream the album on the device. It may sound like I’m making it seem like it’s a cash grab, but that’s because it is. Anyway, this article isn’t about the Yoto.

Build Your Own Local ChatGPT - Part 3: Voice, Vision, and Memory

Mon, 20 Apr 2026 00:00:00 +0000

Author’s note: yes, this header image was once again generated by my own personal GenAI assistant. I swear it is getting slightly better each iteration.

Welcome back to Part 3 of our journey to build a self-hosted, ChatGPT-style AI assistant. In Part 1 we got the hardware and base stack running (Ubuntu, Docker, Portainer, Ollama, OpenWebUI). In Part 2 we dove into models - where to find them, how to pick them, and what quantization actually means for your VRAM budget.

Build Your Own Local ChatGPT - Part 2: Choosing & Loading Your LLM Brains

Thu, 26 Feb 2026 00:00:00 +0000

Author’s note: this header image was generated by my own personal GenAI assistant, and very poorly I might add.

Welcome back to the second part of our journey to build a self-hosted, ChatGPT-style AI assistant! In Part 1, we covered the foundational setup: getting Ubuntu, NVIDIA drivers, Docker, Portainer, OpenWebUI, and Ollama all up and running on your local machine. You now have a working chat interface, even if it’s currently running a basic model.

Build Your Own Local ChatGPT - Part 1: Getting Started

Thu, 25 Sep 2025 00:00:00 +0000

Author’s note: this header image was generated by my own personal GenAI assistant, and much of this blog content was edited down by it as well.

Does anyone else ever worry that one day all your conversations with ChatGPT could be exposed? Or that your information will be out there to be data-mined and trained upon?

“Well, I have nothing to hide,” you say. Sure, neither do I. But it’d be embarrassing if my photo of this “random mark on my foot that won’t go away could this possibly be cancer” ever got out.