Saturday, January 21, 2023

Show HN: Test-driven development spreadsheet to track ChatGPT's failures https://ift.tt/GAPmdao

Show HN: Test-driven development spreadsheet to track ChatGPT's failures The recent discussion on "test-driven development"[1] made me want to track some of the most obvious failings I observe in ChatGPT. Here is my publicly viewable spreadsheet: https://ift.tt/ey56dIk You can add to it by completing the questions (just two are required, the prompt it got wrong and its wrong answer): https://ift.tt/VxpQrH3 Feel free to list any other failures you've observed! [1] https://ift.tt/LCFvIGd January 22, 2023 at 03:10AM

No comments:

Post a Comment

Show HN: Playwright Best Practices AI SKill https://ift.tt/fodWJZ3

Show HN: Playwright Best Practices AI SKill Hey folks, today we at Currents are releasing a brand new AI skill to help AI agents be really s...