For this post, I wanted to take a look at general purpose time series foundation models. In particular, I am curious about what the “general” part of these models actually entails. It is not intended as a throughout benchmark, but more as an exploratory exercise.
I will start with a short intro about why foundation models for time series are in a different category compared to language or vision models, with an overview on what has been released the last year or so.
For this one I wanted to explore two options for secure execution of AI-generated code: E2B, a cloud-based platform using microVMs, and AgentRun, which combines Docker-based execution with safety mechanisms. We will also examine a case study to highlight key differences between the two in terms of setup complexity and execution speed.
Let’s get started (unless you want to jump to the conclusions TLDR;).
Dedicated runtimes for executing AI-generated code allow agentic systems to execute code without compromising the security of the host. Typical features include memory and CPU constraints, file system isolation, and restricted network access.