alt Hacker NewsNeither of those things are true?
Also you are seriously comparing process startup time with the latency of a network call, or worse an llm call?
Neither of those things are true?
Also you are seriously comparing process startup time with the latency of a network call, or worse an llm call?
Yes, if the SaaS application needs to fork subprocesses for every little step of agentic workflows.
Welcome to CGIs, a great 1990's technology for Web applications.