
I don’t know if it’s just me, but over the last few months I feel like I’ve been getting worse and worse results from ChatGPT. I’ve taken to running various OpenAI, anthropic and models in an OpenWebUI instance for anything important, and lately OpenAI is consistently at the bottom of the list.
Back in the old days (ie 2020) we called this “writing out requirements” and it was generally the way that devs knew what they were supposed to do.