1. "ChatGPT Has Passed the United States Medical Licensing Examination (USMLE)" - https://news.ycombinator.com/item?id=34483030
2. "Show HN: Medical LLM API on par with Google Med-PaLM 2. 92% USMLE accuracy" - https://news.ycombinator.com/item?id=37038021
3. "Med-PaLM 2 reaches a score of 86.5% on MEDQA (USMLE)" - https://news.ycombinator.com/item?id=35971465
And for comments:
1. "[...] akin to passing the bar or USMLE could go a long way to solving this problem [...]" - https://news.ycombinator.com/item?id=43315182
2. "[...] very clear that there will be significant disparities by race in USMLE boards in pretty much exactly the same pattern [...]" - https://news.ycombinator.com/item?id=43234441
3. "[...] Suggests MEDIAN USMLE step 1 scores for White, Asian, Hispanic/Latino, and [...]" - https://news.ycombinator.com/item?id=43226207
Generally find HN search works very well, being fast and comprehensive.