Have large language models plateaued
A Hacker News thread debates whether large language models have plateaued or whether recent gains come from better tooling and applications, with autonomous Artificial Intelligence agents showing striking demos and notable failures.
Intel completes ‘Project Pelican’ Malaysia packaging fab for EMIB and Foveros
Intel has entered the final phase of its ‘Project Pelican’ advanced packaging complex in Malaysia, with the site 99% finished and an additional $200 million planned to complete the facility. The site will support EMIB and Foveros flows and help address orders from large Artificial Intelligence customers.
Fujitsu details Monaka roadmap for Arm servers with built-in Artificial intelligence acceleration
Fujitsu unveiled details of its Arm-based Monaka datacenter processors at Technology Update 2025, with the first 2 nm chips due in 2027 and subsequent designs adding integrated Artificial intelligence acceleration through 2031.
China eyes chip-stacking to narrow gap with NVIDIA
Wei Shaojun said China could narrow its technology gap with NVIDIA by stacking 14 nm logic chips with 18 nm DRAM and new compute architectures. The approach is aimed at improving Artificial Intelligence performance and energy efficiency while relying on a fully domestic supply chain.
Pat Gelsinger’s xLight gets tentative U.S. support for EUV FELs
The U.S. Department of Commerce has signed a non-binding letter of intent to support xLight, a venture-backed startup focused on EUV Free Electron Lasers, under the CHIPS and Science Act, paving the way for (up to) $150 million in government funding. The company, which added Pat Gelsinger as executive chairman, plans to build its first system at the Albany Nanotech Complex.
NVIDIA and AWS expand full-stack partnership for Artificial Intelligence infrastructure
At AWS re:Invent, NVIDIA and Amazon Web Services expanded a strategic collaboration to integrate interconnect technology, cloud infrastructure, open models and physical Artificial Intelligence, with AWS adding support for NVIDIA NVLink Fusion.
AWS releases Trainium3 ASIC for Artificial Intelligence workloads
AWS introduced Trainium3, a purpose-built ASIC for Artificial Intelligence workloads, at re:Invent. the chip delivers 2.52 PetaFLOPS of FP8 compute per chip and is available in Amazon EC2 Trn3 UltraServer instances.