Having a very dangerous AI standoff at work, where people are debating wether or not to use a particular connection pooling / threading strategy to fix a production issue, and everyone is unqualified to answer and is instead arguing what their agent said.
They are just straight up admitting they don't know anything, and advocate fiercely for their agent's recommendation.
No one cares, no one tries to stop this behavior. It's seen as good, apparently. I admitted that I don't know enough to have an opinion at the moment, I certainly don't know how to judge the contradictory opinions of multiple frontier AIs, and I fear that just made me look incompetent.
Run both. Benchmark them. Performance is notoriously difficult to predict and much easier to test. If you have a load balancer, run the new strategy on one or two servers and see how their throughput compares to the others.
Exactly! It got so easy nowadays to use AI to setup scenarios since the busy work of writing code/test harnesses and setting things up for the benchmark is done by the machine. Then throw away what does not work.
Some benchmark that would take weeks to plan, code and set up is now hours and days - the time is now spent on the benchmark itself, not on temporary code.
Not an AI defender but this doesn't sound all that different than before where people were just arguing for their understanding of the issue. No one knows everything and has perfect alignment with reality. I'm with the other guy who responded, test it, else y'all just guessing and arguing who's better at guessing.
My hope is they would have read some expert sources and gained some of the expertise required to analyze the issue properly. We don’t seem to do that anymore.
They are just straight up admitting they don't know anything, and advocate fiercely for their agent's recommendation.
No one cares, no one tries to stop this behavior. It's seen as good, apparently. I admitted that I don't know enough to have an opinion at the moment, I certainly don't know how to judge the contradictory opinions of multiple frontier AIs, and I fear that just made me look incompetent.