We're a group of makers shipping together. We help each other stay accountable and reach our goals.
Apply for access
Uwe Dreiss
PRO
@uwe
Thanks so much! Very interesting. So that's sort of text-to-sql (or vice versa)?
Any resources where I can go down a bit of a rabbit hole for a few hours and learn more about it?
So my understanding would be that in case 2 I would send in the prompt itself something like
table: my_table
fields: id INT; name VARCHAR, email VARCHAR, country VARCHAR
And then if I e.g. ask how many people in my app are from the UK, I'd send the query + the table structure in the prompt and it would probably return something along the lines of SELECT count(id) FROM my_table WHERE country = UK, right?
So depending on the complexity of the database (and how often it changes), it still might be a bit tricky, especially if I have relational tables that connect multiple tables via IDs, etc. as this might need additional explanations in the prompt. If I'd use one of the big LLMs, such as OpenAI, what sort of model would work best with this?
Yes, it's text-to-sql. I would just dump your entity relationships into the prompt and ask for the SQL for some example questions. Then, I'd take those and correct the SQL so that it works -- either asking the LLM to correct bugs you see or just doing it by hand. Then I'd put those input-output examples into the prompt and try it on new things and rinse & repeat.
o1-preview will do best, but once you have a good prompt that works well, I would try that out on 4-o and smaller models
There are a few Fintechs in Europe that give you Spanish IBAN's. A lot of my Dutch friends in Valencia talked about a Dutch Fintech that does that. That was a few years back though. Also, I used Sabadell when I lived in Valencia and it was ok. Nothing to complain about to be honest.
I think tech leads and project managers might be more willing and capable of writing good articles. They’re used to writing a lot anyway
Last year, at InvoiceBerry, we randomly started receiving dozens of signups from Sri Lanka. The next day again, and again. Initially I thought it was spam, but they seemed to use the tool. So I reached out to a few people and one of the new signups shared a video with me. Apparently a Sri Lankan influencer mentioned InvoiceBerry in his TikTok video.
So yeah, maybe reach out to some of those sig ups that seem active and ask.
This is great advice! I've seen a few situations now too with an influencer sending a mass amount of engagement from a specific niche or region.
Also, you probably already have but check the email addresses - if they all follow a similar pattern it's probably spam. And timings too - do they come through in batches or are they very evenly spaces (i.e. every 5 minutes), can be a spam indicator of automation (but you probably already are on top of that).
I found it was a youtuber who mentioned me! Good tip
Awesome! This really helps. I started going down a rabbit hole of text-to-sql too :)
Cool! Happy to help. I'd love to hear how you get on.