Google allegedly instructed contract workers evaluating Gemini not to skip any prompts, regardless of their expertise, TechCrunch reports based on internal guidance it viewed. Now, contractors have allegedly been instructed not to skip prompts that “require specialized domain knowledge” and to “rate the parts of the prompt you understand,

Days after Google Deepmind touted its work toward factual accuracy, reports indicate its evaluation policies could be doing the opposite

There's no arguing that AI still has quite a few unreliable moments, but one would hope that at least its evaluations would be accurate. However, last week Google allegedly instructed contract workers evaluating Gemini not to skip any prompts,