41–46 of 46 posts
Keeping the orchestration (and state changes) outside of the LLM is where my thinking is at until I can figure out the answer to that question (among others).
From a practical point of view, what are people thinking about what is considered trustworthy input? Is the data in your CRM trusted? Keeping the orchestration (and state changes) outside of the LLM is where my thinking is at until I can figure out the answer to that question (among others).
I am confused this article does not talk about taint tracking. If state was mutated by an agent with untrustworthy input the taint would transfer to the state, making it untrustworthy input too, so the reasoning of the original trifecta with taint tracking is more general and practical. I am also also investigating the direction of tracking taints as scores rather than binary as most use cases would otherwise be impo…
From a practical point of view, what are people thinking about what is considered trustworthy input? Is the data in your CRM trusted? Keeping the orchestration (and state changes) outside of the LLM is where my thinking is at until I can figure out the answer to that question (among others).
Anything an adversarial attacker might be able to populate is untrusted. If there's a form they can use to add things to the CRM then that's tainted too.
I don’t know if it’s just me but doesn’t a huge value of LLMs for the general population necessitate all 3 of the circles? Having just 2 circles requires a person in the loop, and that person will still need knowledge and experience and a low enough throughput to meaningfully action the workload otherwise they would just rubber stamp everything (which is essentially the 3rd circle with extra steps)
Boiling down all knowledge work to the following workflow:
Inputs -> Analysis -> Action
There would be value to just be able to put an LLM in a loop ("Go get inputs. Make decision. Take action.").
What I think is going to happen is that the human in the loop is going to end up being an engineer/super user who builds a program/workflow that uses the LLM for the Analysis with the Action step being launched externally from the LLM based on the LLM's response.
Inputs (Workflow calls LLM) -> Analysis (Inputs + Analysis Prompt + Instructions to return payload in specific format) -> Action (Check payload and take action)
It doesn't solve prompt injection but mitigates some of the risk while still leveraging AI to make business move cheaper and faster. (Quality being the factor other than Time and Cost for measuring a task and the factor I am not speaking to.)
I don’t know if it’s just me but doesn’t a huge value of LLMs for the general population necessitate all 3 of the circles? Having just 2 circles requires a person in the loop, and that person will still need knowledge and experience and a low enough throughput to meaningfully action the workload otherwise they would just rubber stamp everything (which is essentially the 3rd circle with extra steps)