Skip to main content
OpenAI is working to make GPT-4 less lazy.

The company acknowledged on Thursday that ChatGPT has been phoning it in lately (again), and it’s fixing it. Then overnight, it made a series of posts about the chatbot training process, saying it must evaluate the model using certain metrics — AI benchmarks, you might say — calling it “an artisanal multi-person effort.”

You know, like bread with seeds in it.