This might be interesting if it pulled data from Meta properties (e.g. the Instagram accounts I am following) in order to personally contextualize its responses.

I'm surprised the chatbot on Instagram doesn't already have that. Giving an LLM access to a highly personalized search tool (the scroll algorithm) would make asking for recommendations so much better.

Meta can turn this App into a sort of my assistant. I can dump any link into it. And since those links form the basis of my worldview helping the assistant understand me better. Currently only Google has a monopoly on such a possible futuristic assistant.

No citations.

It's an analysis of publicly available data.

This is public knowledge. Google 'spy insider trading', and click news.

Do you also require medical examination to identify shit stuck to your shoe?

Either Perfect or Dagster. FWIW, the Dagster team is actively reducing the learning curve with each release.

Bond, Perpetual Bond

Interest compounded, not simple.

Dagres missed network effects as the moat.

Skip hospital doctors because they don't make purchasing decisions. Doctors who own their own practice either outright or as a group partner are actually very easy to interview: in the US (assuming where you're located) there are at least a dozen within each county. Have you tried door-to-door? I helped a friend with healthcare customer discovery interviews for a few months, and it's surprisingly effective.

Hold on! It is hard for me (not in US) to get a walk in appointment when actually sick. And they will have reception staff that wont take BS, so what is the play? Is it literally lobby at closing time and catch them on the way to the car?

Not quite, they are small business owners. Small businesses need revenue to stay afloat, so they like to make and save money. You can target them like any other small business. Ask for the person around with the most authority (doc is probably with patients), tell them you can save them money and how you can do it or to see if they can set up a meeting of some kind with their business manager (whoever that is), hopefully they pass it on to their boss.

At least this is my naive understanding

Here's a question you can ask yourself: "where does my context fall within the distribution of human knowledge?" RAG is increasingly necessary as your context moves towards the tail.

Any word which model they used?

Some argue it’s gotten worse due to recent tradeoffs between privacy and accuracy, such as the negative effect Apple’s ATT has purportedly had on Meta’s targeted ad efficacy.

Would have been a great April Fools'.