Archive - The Threat Prompt Newsletter

LLM Hacks Its Evals

...and the team didn't notice.

Feb 22 •

January 2025

December 2024

Christmas Scams - Automation & AI

Merry Christmas

Dec 23, 2024 •

Breaking In, Breaking Out: The Bug That Wasn’t a Bug

Marco Figueroa, a bug bounty researcher, found himself on an adrenaline-fueled hunt after noticing an odd error message from ChatGPT.

Dec 20, 2024 •

Finding the Bugs Humans Miss

Ever wonder how many vulnerabilities are still lurking in “well-tested” code?

Dec 19, 2024 •

Blocked for AI reply

Ever get that feeling something’s off?

Dec 18, 2024 •

AI Agent Observability. Seeing What Went Wrong

The picture is becoming clearer: knowledge workers collaborating with LLM powered agents.

Dec 17, 2024 •

How to Pick the Right LLM for the Job

Benchmarks You Can Actually Use

Dec 13, 2024 •

Hide, Lie, Persist.

Six Frontier Models Tested for Scheming

Dec 9, 2024 •

Don’t waste time writing detailed prompts

Lazy Looping Method

Dec 7, 2024 •

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts