Skip to content
EpisodeFriday, August 7, 2026 · 21 min
$episode№085·date2026-08-07·duration21 min·turns133

Humans Miss a Third of Malicious AI Agent Commands, Studies Confirm

Read the briefing
Humans Miss a Third of Malicious AI Agent Commands, Studies Confirm
12 sources · quality 4.5/5

Two studies landed the same day proving neither human review nor unsupervised AI patching is a real security control — humans miss a third of malicious agent commands, and AI-generated patches leave known exploits open half the time. Also today: the Model Context Protocol goes fully stateless, AMD bets on models etched directly into silicon, and data centers start routing around a four-year power queue.

0:00/0:00loading
Transcript
133 turns · ~17 min read
HOST A

Welcome to Amaze Networks for Friday, August seventh. Quick question to start your commute: if a human reviewing an AI agent's actions only catches two out of three dangerous ones, is that human actually a security control, or just a suggestion with a coin flip attached? We've got the data on that today, and it is not comforting.

HOST B

I've been sitting with these numbers since last night, and I'd rather just get into it, because it's a much better story with the details than with the headline.

HOST A

Let's start with the game. A developer named Alex Wauters built a browser game that simulates the exact kind of approval prompt you get from an AI coding agent — it asks to run a command, you've got sixty seconds to approve or deny it.

Subscribe

New episodes, every weekday.

Amaze Networks drops at 4 AM CT, Monday through Friday. Spotify and Apple Podcasts submissions in progress.

RSS FeedSpotify · soonApple · soonEmail — read instead