ai - 9 min read
73 posts in ai
Learn how speculative decoding pairs a small draft model with a large target model to speed up local LLM inference, and how to run it with Jozu Rapid Inference Containers.
Recap of our webinar with Jozu CEO Brad Micklea: the five levels of AI adoption, the two gaps that get organizations hurt (the AI supply chain and the runtime), real-world attacks, and four actions to take this quarter.
Identity and access management (IAM) and data loss prevention (DLP) weren’t built for AI agents. Here’s where each fails, and what the missing security layer looks like.