In the first episode of an "AI in the shadows" theme, Chris and Daniel explore the increasing concerning world of agentic misalignment. Starting out with a reminder about hallucinations and reasoning models, they break down how today’s models only mimic reasoning, which can lead to serious ethical considerations. They unpack a fascinating (and slightly terrifying) new study from Anthropic, where agentic AI models were caught simulating blackmail, deception, and even sabotage — all in the name of goal completion and self-preservation. Featuring:<ul><li>Chris Benson – <a href="https://chrisbenson.com/">Website</a>, <a href="https://www.linkedin.com/in/chrisbenson">LinkedIn</a>, <a href="https://bsky.app/profile/chrisbenson.bsky.social">Bluesky</a>, <a href="https://github.com/chrisbenson">GitHub</a>, <a href="https://x.com/chrisbenson">X</a></li><li>Daniel Whitenack – <a href="https://www.datadan.io/">Website</a>, <a href="https://github.com/dwhitena">GitHub</a>, <a href="https://x.com/dwhitena">X</a></li></ul>Links:<ul><li><a href="https://www.anthropic.com/research/agentic-misalignment">Agentic Misalignment: How LLMs could be insider threats</a></li><li><a href="https://huggingface.co/agents-course">Hugging Face Agents Course</a></li></ul>Register for <a href="https://practicalai.fm/webinars">upcoming webinars here</a>!

Podurama

Home

Trending

Personal

Your Podcasts

New Episodes

My Files

Favourite Episodes

Tags (Folders)

Recently Played

Bookmarks

Followed Playlists

AI in the shadows: From hallucinations to blackmail

Practical AI

AI Chapters

AI Insights

Reviews