Hard lessons2024-02-17 · Archive
Automated Unit Test Improvement Using Large Language Models at Meta
Original EnglishWhere this applies — and where it may not
Original English evidence, selected for practical experience and outcomes. Read the source discussion for context.
From the discussion
“I don’t think a human engineer with 25% failure rate would be very helpful, if it’s a certain kind of failure.”
@bbor · View source
Y
Automated Unit Test Improvement Using Large Language Models at Meta
@bbor · 301 points · 188 comments
Read the Hacker News threadSource: OpenIndex Hacker News dataset (ODC-By). Original content belongs to its authors. Summaries, translations, and suggested steps are AI-assisted editorial work. Read the sources; individual outcomes are not guarantees.