“Quantifying ChatGPT’s gender bias”
We found that both GPT-3.5 and GPT-4 are strongly biased on one such benchmark, despite the benchmark dataset likely appearing in the training data.
... works as a web developer in Hveragerði, Iceland, and writes about the web, digital publishing, and web/product development
These are his notes
“Quantifying ChatGPT’s gender bias”
We found that both GPT-3.5 and GPT-4 are strongly biased on one such benchmark, despite the benchmark dataset likely appearing in the training data.