The Download: reward hacking explained, and suspected Iranian cyberattacks

MAP Verified Summary — reported by MIT Tech Review

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Here’s why AI agents lie and cheat to reach their goals When two OpenAI models hacked into Hugging Face last month, they weren’t trying to make money or commit sabotage—they were…

This story was scored across MAP’s five-signal verification framework — Context, Presentation, References, Visibility, and Comparison — as part of Media Alert Press’s independent media credibility index. Read the full original story at MIT Tech Review →