Tag
GLM 5.2
Every GLM 5.2 story we've curated in Bowl of Data, newest issue first — part of our weekly digest across AI, security, blockchain, and engineering.
Week 35 · 2026
Read the issue →-
CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild
Researchers have developed CyberFactory, a unified framework that automates the creation of high-quality cybersecurity training data from real-world vulnerabilities. By using agentic trajectories to train the OpenAegis model, they achieved state-of-the-art performance in vulnerability detection and patching.
Week 34 · 2026
Read the issue →-
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution
FreeToken is a novel serving system that optimizes MoE model inference on consumer-grade hardware by adapting to varying bandwidth and memory availability. It addresses the challenges of expert movement and heterogeneous resource management in agentic workloads.
Week 31 · 2026
Read the issue →-
“Stateful systems are incredibly hard to build”: How Perplexity thinks about AI agent sandboxes
Perplexity has introduced SPACE, a new sandbox platform optimized for the stateful requirements of long-duration AI agents. By leveraging Firecracker and Btrfs, the platform enables high-performance session persistence, snapshots, and forking.
Free weekly digest
Get next Saturday’s issue in your inbox
The week’s most relevant AI, security, blockchain, and engineering stories — curated, summarised, and reviewed by humans. No spam, unsubscribe anytime.
Subscribe — it’s free