AI chatbots change 'personality' depending on the language, study finds
Chinese researchers studied whether chatbots answer differently depending on the language used. They report that prompts in Mandarin made the language models more open-minded.
Related stories
The thin orchestrator: how Meta made its AI agents more reliable by giving the router less to do
Meta engineers report better efficiency and accuracy in their data pipeline agents by keeping the orchestration layer deliberately thin. The orchestrator only routes work and enforces reliability checks, while specialized agents handle the domain reasoning.
GenRecs tokenization: how Meta is transforming ads recommendation with a stable model vocabulary
Meta describes Generative Recommenders, which reason about ad content and user preferences together instead of scoring every ad, drawing on the world knowledge in LLMs. GenRecs tokenization is the data representation underpinning the approach.
From microservices to agents: the next evolution of distributed systems
This article by Mallika Rao looks at the shift from microservices to agentic AI architectures. Where microservices split up functions, agent systems split up decisions, which brings new challenges for observability, reliability and design.
AI researchers stranded Claude on a virtual desert island. It started to "play"
To see what AI agents do when given no task, researchers repeatedly left copies of Claude Opus 4.7, nicknamed Eko, alone on a virtual desert island for 30 hours. What the agents did with their time looked a lot like play.
With Minions, Apple wants to use idle Mac GPUs for inference
Apple has published research on Minions, a system that pools unused GPU resources across clusters of Apple Silicon Macs to run AI inference. The idea is not new, but the work builds on existing approaches and further positions the Mac as an AI machine.