FM News
It passed CI. It passed your evals. The customer still got the wrong answer.
◆ 85RelevanceOn a story from The New Stack7h ago
Read the original at thenewstack.io
It passed CI. It passed your evals. The customer still got the wrong answer.
fmode.me/n/it-passed-ci-it-passed-your-evals-the-customer-still-got-the-wrong-answer
More from FM News
Chip Huyen explains how to cut inference costs without new hardware1 pts · The New Stack“Machine translation is still broken for most of the world’s languages”: Cohere builds non-reasoning for a reason1 pts · The New StackHarvey Puts a Former Practicing Lawyer in Every Deployment. About 180 of Them. Here’s How That Model Works1 pts · SaaStrOpenAI’s Sam Altman says it would be ‘ill-advised’ to go public in 20261 pts · TechCrunch AI