Prompt injections, malicious code, and AI agents: In this week’s Five-Minute Friday, Jon Krohn looks into the current security weaknesses found in AI systems. A structural vulnerability that The Economist dubs a “lethal trifecta” could cause havoc for AI users, unless we take the necessary steps to contain our systems. 
Additional materials: ⁠⁠⁠⁠⁠⁠<a href="https://www.superdatascience.com/928">⁠⁠⁠⁠⁠⁠⁠www.superdatascience.com/928⁠⁠⁠⁠⁠⁠⁠</a>

Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.

Podurama

Home

Trending

Personal

Your Podcasts

New Episodes

My Files

Favourite Episodes

Tags (Folders)

Recently Played

Bookmarks

Followed Playlists

928: The “Lethal Trifecta”: Can AI Agents Ever Be Safe?

Super Data Science: ML & AI Podcast with Jon Krohn

AI Chapters

AI Insights

Reviews