raxy

Your last line is actually very insightful. I was just looking at LLM from the chat app perspective.

I wonder how open these services will be to data storage if they do become a "universal app". If I used LLM to make an app for tracking training for endurance running, and I slapped an 800kb .fit file in there each day, the storage for all of these files would probably be fine, but without condensing each run down to a textual summary like Garmin/Strava currently does ("You ran 10km in 35:00, at a pace of 3:30/km. This improved your speed/{vague motivational LLM quote}"), wouldn't the context become enormous after a pretty short duration, causing huge costs? Genuinely curious.

If it works for you, that's great.

Is a "recent orders" or "reorder" feature not enough to meet this demand if you frequently order the same thing from the same place? I don't quite understand the need for a middleman LLM here.

When you're asking for suggestion, is that a completely random suggestion to try new dishes or a pre-selected range to randomise from a choice of things you've already pre-screened?

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.

Just wanted to say, I think this is actually a really good idea.

My (honestly hardliner) view for a while has been that ads shouldn't exist. If a product was really good (and was in demand) a consumer would seek it out. This would entail the consumer knowing first the problem they want to solve, and then secondarily what the solution might look like, and once having found a few different products that satisfy their solution, carefully analysing each and working out which one they want.

Your idea of a directory neatly aligns with the way I view the market. Nobody should be putting an advertisement in front of people, they should be sought out when a need has to be met.

Not to mention the amount of environmental problems, human time and labour we could spare if our world wasn't oriented around fashions, trends, and attention harvesting.

I'm sure such a setup would devastate the world economy, so obviously it'll never happen. We need everybody to be sat away designing, manufacturing, transporting and marketing junk to each other all the time, to keep the market ticking. Sometimes the current adtech-led / "gamblification" of the economy makes me imagine we're in the endgame, pretending that fad creams, supplements, gadgets and trinkets are somehow worth something, and therefore, so is all the advertising that is being used to sell it.

Don't tempt us all with a good time.

Am I one of very few people that believes LLM apps don't solve or replace a large number of apps.

Take all these basic lifestyle CRUD apps. Maybe it's a skill issue on my part, but whenever I've tried to use LLM apps over any sort of medium-to-long-term time scale for tracking something (ie. endurance running training), within about a month it begins hallucinating, recalling the wrong things, linking the wrong bits of data to other bits of data (dates, distances, heart rate data, workout paces etc), and it does all of this even when pointed to a basic spreadsheet or simple text file to keep it onboard with what happened where. It just seems to look at these files, and then look at it's own context and confuse all the details based on its own context.

Every other month, some brand new shiny model is released and it's exactly the same deal every time. I think the underlying technology simply can't deal with these sorts of goals. A whole range of apps for lifestyle tracking don't seem under threat, in my opinion, if this is the best its capable of.

Many other things I can't imagine wanting an AI to do for me, especially anything involving payments, bookings. There was a discussion the other day on here about AI being used to order takeout. Why would somebody want to delegate one of their last personal decisions to a LLM?

I suppose there is levels to all of these things. For somebody who uses apps to obtain most of their food, this is probably the next step.

Ordering off of DoorDash (or whatever equivalent app elsewhere) in general seems to be the worst possible way to acquire and eat food, in my personal opinion.

Everything on these apps is nutrition-zero junk, filled with salt, oil and sugar, charged at a premium. I ate it in the past, and nowadays I couldn't be paid to eat it. Self-cooked meals beat them in every way, including convenience.

Is fast food/delivery food so frequently used that this is now warranted?

Even at my most gluttonous, many years ago, I would order maybe a single takeaway every other week, and when I did that, I'd want to be in complete control to browse and try new things. The only use case I can see for AI is as an alternative to traditional search to work out what some unknown ingredient is, however if I recall, most takeaway apps are just pictures with a name.

People who eat fast food more than once a week need to seriously assess how bad this food is for them. It's overly salted, oily and greasy junk with next to no nutritional value. And for what is it, it is ridiculously expensive. The people that eat it often are stuck in a trap.

For less than half of the cost of the lowest value takeaway (around £20.00, although I've seen people carrying bags with receipts up to £50!), you can buy a whole chicken, potatoes and vegetables, which can cover up to 3 or 4 meals. £10 for 3 meals or £20-50 for 1. You just need to put things in ovens and pots and wait, the same as you have to tap on your phone and wait.