future Rob

Getting feedback that my light design looks like an insertable should I pivot

Looking forward to running local models on my new rig

My dryer solved the navier stokes problem!!

Just finished setting up my first Isaac sim environment

🤔

will this alibaba rig compromise my network

Remember when teenage engineering designed Raven R for Baidu

Adobe's last hope is to bring back Flash

Office goals

When fine-tuning small LLMs, it's interesting to see which anchors are established. For the most part, at 4-bit quantization, very little personality is preserved, but certain functions do seem to peek through. This fine-tuning is made from my entire ChatGPT conversation dataset of around 9k conversations.