はてなブックマーク

OpenAI is keeping the architecture of GPT-4 closed not because of some existential risk to humanity but because what they’ve built is replicable. In fact, we expect Google, Meta, Anthropic, Inflection, Character, Tencent, ByteDance, Baidu, and more to all have models as capable as GPT-4 if not more capable in the near term. Don’t get us wrong, OpenAI has amazing engineering, and what they built is

The text below is a very recent leaked document, which was shared by an anonymous individual on a public Discord server who has granted permission for its republication. It originates from a researcher within Google. We have verified its authenticity. The only modifications are formatting and removing links to internal web pages. The document is only the opinion of a Google employee, not the entir

Networking is a critical part of any datacenter, especially with the rise of networking-intensive large language models. As such, it was a clear target for Google’s infrastructure optimization efforts. Over the last year at conferences such as OFC and SIGCOMM, Google disclosed their custom networking stack, Jupiter, from in-house switches all the way through to custom reconfigurable software. This

The 1,000-foot summary is that the default software stack for machine learning models will no longer be Nvidia’s closed-source CUDA. The ball was in Nvidia’s court, and they let OpenAI and Meta take control of the software stack. That ecosystem built its own tools because of Nvidia’s failure with their proprietary tools, and now Nvidia’s moat will be permanently weakened. TensorFlow vs. PyTorch A

Arm is widely regarded as the most important semiconductor IP firm. Their IP ships in billions of new chips every year from phones, cars, microcontrollers, Amazon servers, and even Intel's latest IPU. Originally it was a British owned and headquartered company, but SoftBank acquired the firm in 2016. They proceeded to plow money into Arm Limited to develop deep pushes into the internet of things,