Richard Wei
@rxwei
ID: 71512330
04-09-2009 11:25:47
498 Tweet
3,3K Followers
295 Following
Don't miss this new guest blog post by Tarek M. Ben Lechhab! LLMs Calling LLMs: Building AI Agents with Apple's Foundation Models and Tool Calling Explore going from prompts to multi-agent architecture by leveraging Foundation Models tool calling capabilities and exposing LLMs themselves
NatashaTheRobot Julian Schiavo Ok, that’s good to hear! We are tracking a known issue: the framework may throw a guardrail violation for all prompts, where the actual reason is that the model assets haven’t been fully downloaded. (FB18944619)
Shihab Mehboob You need to recompile your app using Xcode 26 beta 5 to run the app on OS 26 beta 5. We made some final API improvements and removed APIs that were deprecated in previous betas.
Rudrank Riyam That’s right — guardrails will no longer be triggered by sensitive/controversial topics that are not fundamentally unsafe. If you ask the model to summarize or rewrite such content, the model will do as told; otherwise, the model may still refuse with an explanation.
My Dark Noise update with the new iOS 26 Liquid Glass design, and a new Magic Mix feature (demoed here) powered by the new Foundation Model API & Apple Intelligence is ready for tomorrow's release! If you're press writing about app updates, my press release is below 🧵👇