[0] https://github.com/microsoft/aici/blob/main/controllers/aici...
[0] https://github.com/microsoft/aici/blob/main/controllers/aici...
In addition to constraining output, AICI also lets you fork the generation programmatically as well as dynamically edit the prompt which is important in some scenarios.
The idea is that several LLM inference systems implement AICI as an interface, and Guidance, LMQL, etc implement AICI backend and then everyone wins.
Having a common interface (provided it is adopted) lets you re-use the same controller over multiple LLM infra stacks (and different models), or conversely the different controllers over your own brand new LLM infra stack (or model).
Using Wasm simplifies your deployment story in the cloud (sandboxing), however the AICI runtime communicates with controllers as separate processes and so if the controller is trusted it could in principle be run in native code.