I think it's all about keeping state in the determinant space. I've come across the same issue, the key was to not rely on LLM performing workflow - the runtime needs to enforce.
Author here. The TL;DR: move rules from prompts into types the compiler refuses to violate, then bounce the AI coding loop off those refusals. The repo is github.com/pyrex41/Shen-Backpressure. Builds a lot on Geoff Huntley's backpressure idea -- none of this is rocket science, just an effort to apply sound programming principles in a world of LLM coding agents.
Thank you, interesting work. Please, clarify what is possibly a naive question - your README states that the constraints imposed by your tool are weaker than the formal verification guarantees. Why not implement the backpressure as the full formal verification barrier? Too complex to implement?
So, capabilities/type systems. Building code architecture guardrails steep enough the AI won't jump the fence/take shortcuts.
I think it's all about keeping state in the determinant space. I've come across the same issue, the key was to not rely on LLM performing workflow - the runtime needs to enforce.
Author here. The TL;DR: move rules from prompts into types the compiler refuses to violate, then bounce the AI coding loop off those refusals. The repo is github.com/pyrex41/Shen-Backpressure. Builds a lot on Geoff Huntley's backpressure idea -- none of this is rocket science, just an effort to apply sound programming principles in a world of LLM coding agents.
Thank you, interesting work. Please, clarify what is possibly a naive question - your README states that the constraints imposed by your tool are weaker than the formal verification guarantees. Why not implement the backpressure as the full formal verification barrier? Too complex to implement?