Very cool! How much context have you used as input for the LLM for each decision? Would be interesting to test it under different context/assumptions to see how the decisions would change!
Fascinating experiment. The future of AI won’t just be smarter models, it’ll be how well multiple agents coordinate, validate outputs, and handle real-world complexity together.
This is a fascinating addendum to your previous post. The results highlight both the strength of the approach and their (current) limitations. Decisions are made in a "sterile" environment, there are no scars of previous battles won or lost and internal politics, factors that can easily throw decision makers' judgement. On the other hand, there is no subject matter "feel" -no way to really wrap a lifetimes experience into decision making.
It goes without saying that assuming all companies will use AI to inform decision making to one degree or another, the edge will be in use of proprietary data and perhaps by finding a way to force the AI to establish a plausible contrarian case (even in the absence of hard data). It reminds me (in a very roundabout way) of the film "Trouble With the Curve"-written as a response to the Moneyball approach to baseball.
Very cool! How much context have you used as input for the LLM for each decision? Would be interesting to test it under different context/assumptions to see how the decisions would change!
Fascinating experiment. The future of AI won’t just be smarter models, it’ll be how well multiple agents coordinate, validate outputs, and handle real-world complexity together.
This is a fascinating addendum to your previous post. The results highlight both the strength of the approach and their (current) limitations. Decisions are made in a "sterile" environment, there are no scars of previous battles won or lost and internal politics, factors that can easily throw decision makers' judgement. On the other hand, there is no subject matter "feel" -no way to really wrap a lifetimes experience into decision making.
It goes without saying that assuming all companies will use AI to inform decision making to one degree or another, the edge will be in use of proprietary data and perhaps by finding a way to force the AI to establish a plausible contrarian case (even in the absence of hard data). It reminds me (in a very roundabout way) of the film "Trouble With the Curve"-written as a response to the Moneyball approach to baseball.