Full Width [alt+shift+f] Shortcuts [alt+shift+k]
Sign Up [alt+shift+s] Log In [alt+shift+l]

Improve your reading experience

Logged in users get linked directly to articles resulting in a better reading experience. Please login for free, it takes less than 1 minute.

More from PromptArmor Blog

Data Exfiltration from Slack AI via indirect prompt injection

Authors: PromptArmor

7 months ago 35 votes
Announcing LASEC: LLM Application Security Executive Certification

Including a never before seen exploit from PromptArmor's cutting edge threat intelligence team.

a year ago 27 votes
Data exfiltration from Writer.com with indirect prompt injection

Authors: PromptArmor and Kai Greshake

a year ago 22 votes

More in AI

Altman vs Musk cage match

Uh oh. Now Altman wants to build a social media company, to compete with X. Who should we root for?

18 hours ago 2 votes
How much does a 10 million token context window actually cost?

Some back-of-the-napkin math for Meta's Llama 4 Scout

8 hours ago 1 votes
GPT-4.1 Is a Mini Upgrade

Yesterday’s news alert, nevertheless: The verdict is in.

4 hours ago 1 votes
”Those claiming we’re mere months away from AI agents replacing most programmers” should think again

AI agents will change the world. But not this year.

5 hours ago 1 votes
OpenAI #13: Altman at TED and OpenAI Cutting Corners on Safety Testing

Three big OpenAI news items this week were the FT article describing the cutting of corners on safety testing, the OpenAI former employee amicus brief, and Altman’s very good TED Interview.

yesterday 2 votes