We worked with AI (ChatGPT and Claude mostly) to spec an AI server to meet research grade standards for a two person lab. Our goal is to do AI research such as tuning LLMs, implementing LoRA/RAG ...
Over the weekend, some people noticed that GPT-4o is routing requests to an unknown model out of nowhere. Turns out it's a "safety" feature.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback