The lifestyle monitoring thing is something I've been testing with ChatGPT, Gemini, Claude for the last year or two now, and it doesn't ever seem to get any better.

I may be completely out of the loop here, so forgive me if I'm missing details, but I always have and continue to believe that the coding prowess of LLM agents more-or-less comes down to the sheer abundance of data it has trained off of on the web, and that code itself is ideal for LLM by the way it is discrete and syntax-bound, same as the way LLM can write very well provided they've read more-or-less the same sequence of text before in abundance. For the speed advantages it provides in coding, and for the accuracy it has for well-established information, LLM is a very useful technology.

I just don't follow how they are going to do the same thing with such granular telemetry data, such as datasets from a day of nutrition or a workout. The values are continuous, minute, and are so parallel to noise in the way they are provided. Take running. If you dumped a .fit file from a Garmin or other watch with a series of heart rate values, paces, elevation levels, GPS co-ordinates, respiration rate, vertical oscillation etc, and you trained on a bunch of files like this, the values are so discrete that I can't understand how it would connect them and tokenize them across different people or even the same person's various workouts, with the high degree of factors (nutrition, climate, illness/injury state and severity) that can alter those values. It's no longer about just tokenizing text, but with advanced calculations.

I've seen second-hand through friends in running with apps like Runna that it produces plans that aren't suited for them at all. There's simply too many small variables that these things don't seem to be able to map. It gets caught up on summaries of runs. It can give general advice about things, but it doesn't have the level of detail or understanding necessary to give good guidance. Strava "AI" and Garmin "AI" just make a 2-3 line summary from the average data from the entire run or workout.

Perhaps this is something that is already being worked on, and I would be happy if it was, but I just can't personally see how LLM can work with such datasets in a detailed way, beyond the useless summaries Garmin and Strava give "You ran 10km in 35:00, with a pace of 3:30/km. This shows that your speed is improving". I would love an explanation/links on how LLM can get around this if anybody is willing to spend the time providing it. Happy to have my mind changed.

>Now the vast majority of code is written by them.

Is that really true outside of the HN bubble? I'd like to see some studies that back it up.