Maya Murad and Kaoutar El Maghraoui to debrief a few big AI announcements. Last week we covered small vision-language models (VLMs)
⏱ and a new agentic coding tool
and this week Granite 3.2 dropped with new VLMs
can fine tuning on a malicious task lead to much broader misalignment? Our experts analyze a new paper released on ‘Emergent misalignment.’ All that and more on this week's episode!