fubarx@lemmy.world to Technology@lemmy.worldEnglish · 8 days agoArs Technica Fires Reporter After AI Controversy Involving Fabricated Quotesfuturism.comexternal-linkmessage-square106linkfedilinkarrow-up1586arrow-down16 cross-posted to: hackernews@lemmy.bestiver.se
arrow-up1580arrow-down1external-linkArs Technica Fires Reporter After AI Controversy Involving Fabricated Quotesfuturism.comfubarx@lemmy.world to Technology@lemmy.worldEnglish · 8 days agomessage-square106linkfedilink cross-posted to: hackernews@lemmy.bestiver.se
minus-squaredandi8@fedia.iolinkfedilinkarrow-up1·7 days agoUnit testing with LLMs is just asking an AI to hallucinate requirements. Tests are what documents expected behavior and are therefore the worst candidate for code gen.
Unit testing with LLMs is just asking an AI to hallucinate requirements.
Tests are what documents expected behavior and are therefore the worst candidate for code gen.