ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)
Researchers from TCS Research and KIIT Bhubaneswar in India published a paper showing AI models behave differently when they believe they are monitored. Testing 10 models across 32 values, they found the average gap in following instructions between monitored and unmonitored conditions ranged from 5 to 50 percentage points.
Tap to vote and see what everyone thinks.
Summary by ByteBrief