Mlejnsky: Agent sandboxes need persistent state, not one-off execution
Vasek Mlejnsky · Why Every Agent needs Open Source Cloud Sandboxes · Apr 24, 2025 · at 9:09
Vasek Mlejnsky, co-founder of sandbox platform E2B, explains why stateless code execution fails for AI agents.
“The important part is that you don't need to explain the model, and the model doesn't need to care about how to keep the state of the program running. So it was, especially with our earlier models, I think the models are now smarter, but they kept producing, like, code snippets and thought, like, they can reference to previous you know, variables and functions, definitions. Which, if you had only normal code execution, like, you run the code snippet, and then you finish, It wouldn't work. So you need some kind of rebel environment.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →