Piecemakers bets edge AI devices will diverge from reliance on HBM — custom-designed memory fuses DRAM stack directly to the processor using hybrid bonding

## Episode Summary In this episode, we cover: - **Piecemakers bets edge AI devices will diverge from reliance on HBM — custom-designed memory fuses DRAM stack directly to the processor using hybrid bonding** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/semiconductors/piecemakers-bets-edge-ai-devices-will-diverge-from-reliance-on-hbm-custom-designed-memory-fuses-dram-stack-directly-to-the-processor-using-hybrid-bonding) - **Nvidia's DSX Technology Boosts AI Data Center Output 24% on Same Power Budget - finance.biggo.com** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMidkFVX3lxTE9lbzNMQ1h3VzVWbHRZN253N0RMXzdBN3BhZjF1c2p2TVhHVHo0R0hzLUJZLU44VHhRMkw1Smx3VEtnZXljc2tkbTNTT0RaTHdtRVpnWXdDVmtOZW9ySGttOG1yQ3FIZXZaYy1RRmFWTlotdW9GY3c?oc=5) - **How NVIDIA NVLink 6 Delivers Multi-Layer Resiliency for AI Factories** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/how-nvidia-nvlink-6-delivers-multi-layer-resiliency-for-ai-factories/) - **Investigation details how billions' worth of export-restricted Nvidia AI chips are sold to China — report details how Chinese firms skirt Trump's regulations** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/artificial-intelligence/billions-worth-of-export-restricted-ai-accelerators-sold-to-china-report-details-how-chinese-firms-skirt-trumps-regulations) - **d-Matrix, the AI Inference Chip Startup Backed Early by Samsung and SK, Joins Nvidia's Ecosystem - finance.biggo.com** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMidkFVX3lxTFBzWkEwQ1JQNmdGRElSRXBQYTJGYXE5YnVzMG9lRkVkOXNhWnI2REV6YlJxc2REZHBXYm1XN1EyenJoZ0tGY2M1dmtfWFBPaHNtY1Z3N1MzUF94ZVRXTDNRRkJNMVREQkNub2s2LXR0Nml0WDlLWlE?oc=5) --- *Sponsored by Ada, Ago Consulting, and Zen Semiconductor*