🖥 ordered a 32GB Mac Mini Pro so I can do more AI work and have a dedicated machine at home again #mylife

Get OpenAI $2500 Grant (time to ship!) #inpilot

🤖 I built a robot to help generate and maintain some Django/Python code using [cog](nedbatchelder.com/code/cog/in…). This will speed up my prototyping by a lot #myconf

Get invited to the OpenAI o1 beta but decide to nix it for now because it’s wildly expensive and slow with low rate limits, and the cheaper mini model is only tuned for STEM use cases #watchdog !private

🖥 threw some parts together to get a Windows box together so I can run pyautogui on it and build a few things #mylife

🤖 more AI writing project

🤖 checking out Amazon's Astro robot video demo 👀

🤖 sat down and had ChatGPT write some GPT4(ish) code for me

Ordered two Nvidia GPUs to implement some ✨ magic into #2markdown.

🤖 setup my new Raspberry Pi Zero 2 W tonight so that I can run Python on it and connect from anywhere via Tailscale. Time for some hardware projects.

get new notebook for dev work

Working on a distribution strategy for the latest product review on hackernoon: hackernoon.com/i-spent-a-week…

Finished home AI server build: 2 x 2697v2, 128 GB ram, 2 x Nvidia Tesla P40 24 GB gpus. #2markdown

🤖 got sweep running on my Mac Studio and spent $0.73 letting it write five pull requests to try it out. Not bad.

Got $2500 credits from OpenAI time to build something that will make money.

Over the past three days and a half, I've dedicated all my time to developing a new product that leverages locally running Llama 3.1 for real-time AI responses. It's now available on Macs with M series chips – completely free, local, and incredibly fast. Get it: Snapbox.app #snapbox

🤖 more robot work, but figured out how to get better results limiting num_predict for git commit messages #research

Have a GPTini with OpenAI #life

hacking on next AI project

Open Source AI writing app github.com/naveennaidu/novuel