Tracking AI existential risk. Source-backed context. Original reporting always linked.
MONITORING CORE AI-RISK FEEDS · UPDATED HOURLY
Industry

The Download: reward hacking explained, and suspected Iranian cyberattacks

Zac Boring August 3, 2026 1 min read
Read original source →

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…

By Charlotte Jee

Read the full article at MIT Technology Review →