I'll just never feel the same about "insights, advice and support" coming from a LLM vs. a real person. I know that perhaps in a blind A/B testing via text channels I probably won't be able to tell the difference, at least not right off the bat, but there's just something profoundly wrong with humanizing this. Personally I'd very much like an "AI training framework" (tried many but no fit yet), but I don't need a digital cheerleader.
RE: calorie counting, I used to work on a calorie counting app that worked on delivery meals (back in China - nobody cooks there). It was way back then, so we talked to the chefs and had recipes w/USDA-like DBs to estimate calories. The assumption was that you measure your intake from the app and your weight, if it doesn't go up/down as expected, you just adjust a coefficient every N period, i.e. not losing weight? ok let's set all calorie estimates at 1.1x for you. Rinse and repeat until you're losing weight.
Thank you for the reply, I appreciate the feedback
I understand you oppose the very concept of the app, but I would still like to ask: is there something that would actually change your mind? A change in position, a different way of using the LLM, something else?
I am sure there will be lots of people feeling the same, so I am wondering if there is any way to mitigate the problem or I should accept that those users will never use the app
(thank you about the calorie counting part as well, that is truly useful for me)
Perhaps you're right and we will naturally segment into people who embrace anthropomorphic LLMs, and people who prefer tables and checklists and charts. It's ok, we already split into many groups e.g. people who prefer to read paper books vs. people who prefer to listen to audiobooks.