I gave Claude access to a financial model once. Full REF! explosion too. The thing is, it warned me first - 'this might break circular references' - and I clicked through anyway.
The unlock that fixed it: treating Claude like a junior analyst. Not 'update this' but 'explain this formula first, then let's talk about changing it.' Context front-loading before any action.
The finance function is genuinely next. But the interface needs to be task-specific - not 'here's Excel, figure it out.' Wondering if you're seeing the same pattern - does scoping the task tightly change the output quality for you?
Thanks, Ben, for the insights. I used to train aspiring Ph.D.s to work in an area where complex models attempted to simulate physical reality. The challenges were first, to get them to understand that the model was NOT reality and second, to help them develop the knowledge and judgement to know when the models were lying to them. Unfortunately, a lot of Ph.D.s still fail in both aspects.
Hi Ben, love your summaries on business and tech! I've just recommended Serviceable Insights to my subscribers at Protocol Zero Manual. Looking forward to your future posts!
I gave Claude access to a financial model once. Full REF! explosion too. The thing is, it warned me first - 'this might break circular references' - and I clicked through anyway.
The unlock that fixed it: treating Claude like a junior analyst. Not 'update this' but 'explain this formula first, then let's talk about changing it.' Context front-loading before any action.
The finance function is genuinely next. But the interface needs to be task-specific - not 'here's Excel, figure it out.' Wondering if you're seeing the same pattern - does scoping the task tightly change the output quality for you?
Yeah 100%
Definitely need to break it down to smaller components and give much more specific feedback/guidance like an overly eager junior employee
Thanks, Ben, for the insights. I used to train aspiring Ph.D.s to work in an area where complex models attempted to simulate physical reality. The challenges were first, to get them to understand that the model was NOT reality and second, to help them develop the knowledge and judgement to know when the models were lying to them. Unfortunately, a lot of Ph.D.s still fail in both aspects.
Thank you Paul!
Right now these AI systems work like very eager 19 year olds with relentless work ethic but minimal common sense.
Unfortunately this lack of sense seems to apply to older folks too so perhaps we have reached AGI!
Artificial Geriatric Intelligence?
Hi Ben, love your summaries on business and tech! I've just recommended Serviceable Insights to my subscribers at Protocol Zero Manual. Looking forward to your future posts!