> In-browser Postgres
NICE!
> with an AI interface
... uhh
Postgres.new: In-browser Postgres with an AI interface
111–116 of 116 posts
Re: Postgres.new: In-browser Postgres with an AI interface
#112Earlier quoted context omitted.
LLMs don't have the context to make good decisions though. You need all of that hard fought skills to make those decisions. And people are the only ones that can have the context enough to actually make decisions. Not only that, but AI is way more expensive than we think. We're currently in a hype bubble funded by last ditch effort VC money. When that money runs out, and it will eventually, AI is going to get WAY mor…
I personally think LLMs make much better decisions than me. I often have a design in mind and then when I prompt Claude it gives me a much better one, and also takes a lot of edge case into account that I didn't even think of. Maybe I'm a useless programmer but I'm sure I'm not the only one.
Do you use Claude in the web interface/directly prompt it or some tools for that?
Re: Postgres.new: In-browser Postgres with an AI interface
#113This tool is amazing for us. There's so many pieces to this - the capability is a big step forward for architecting databases. Rudimentary compared to what you've done, but is it possible to take an existing database schema, developed either in the Supabase migrations style or another tool like Flyway, and draw the diagram? That alone is huge for us in an enterprise setting, and would allow us to communicate the stru…
> take an existing database schema, developed either in the Supabase migrations ... and draw the diagram? It might not be so obvious, but this diagram tool is already built into the Supabase Dashboard (under "Database") I can see some value in providing this as a generic service for any PG database - I'll look into it - but I know that Dbeaver already has something like this built in (and I think pgadmin too)
Our scenario is trying to produce a diagram during CICD. We have ongoing changes that happen to our SQL codebase, and it's a constant problem to align our documentation and diagrams to that. If we could see the current ER diagram of 'main' branch, and ideally also any given historic commit, it would be huge for our product owners, as they could consume the diagram and understand the current schema without disrupting the engineers. The CICD pipeline would ideally spit out a static page of the ER diagram during build, either as SVG or HTML.
Dbeaver and PGAdmin's diagramming functions aren't anywhere near as advanced as what you've built here, and fall apart for large diagrams. Your team has a lot of smarts!
Re: Postgres.new: In-browser Postgres with an AI interface
#114Earlier quoted context omitted.
> take an existing database schema, developed either in the Supabase migrations ... and draw the diagram? It might not be so obvious, but this diagram tool is already built into the Supabase Dashboard (under "Database") I can see some value in providing this as a generic service for any PG database - I'll look into it - but I know that Dbeaver already has something like this built in (and I think pgadmin too)
Our scenario is trying to produce a diagram during CICD. We have ongoing changes that happen to our SQL codebase, and it's a constant problem to align our documentation and diagrams to that. If we could see the current ER diagram of 'main' branch, and ideally also any given historic commit, it would be huge for our product owners, as they could consume the diagram and understand the current schema without disrupting…
This one isn’t available in that format, but it looks like this open source tool could help:
Re: Postgres.new: In-browser Postgres with an AI interface
#115It is a neat tech demo but it clearly shows the limits of AI: - I got it to generate invalid SQL resulting in errors - it merely generates reasonable SQL, but in my case it generated to disjoint set of tables…. - In practice you have tot review all code - It can point you into the wrong direction. Novel systems often have something smart/abstract in there. This system creates mostly Straightforward simple systems. Th…
I have had tremdendous success with using LLM's to generate SQL. In my use, the majority of the time, ChatGPT gets things spot-on. Even for really sophisticated queries that are going to inspect and aggregate multiple tables into one single output. I do agree it is not perfect - and things need to be reviewed - but I rarely get the sort of gobbledygook that "resembles" valid SQL and is in fact meaningless.
meaningless is good. You can take one look and discard it. The problem is that you can't trust there aren't subtle errors though. So you still need to go everything with a fine toothed comb. If you don't, you're just sitting on a ticking timebomb. "it seems to be working" is very very different to "this does what I had in mind and it will work for all inputs"
Re: Postgres.new: In-browser Postgres with an AI interface
#116Earlier quoted context omitted.
If I did that I would waste so much time. I know what code is in my codebase. Maybe if I was a novice this would be effective to help me learn it. Is the point of the exercise to wow myself for a week that an LLM can spit out solutions?
No its that it will code a days worth of work in a few minutes
I don’t get the exercise here though. If I have a 10K LOC then why would I iterate over the file to make changes? It’s a bad code base. Why wouldn’t I have my LLM break down the file into smaller components so it’s not so daunting every time I need to make a change and require an LLM to save a days worth of work time.
Let’s say there is a reason to keep this 10K LOC together in a single file. I have never had work in SWE that involved making minor iterations to a file over a week where the work took a whole day to complete. I can see how that could happen but requiring a day to change code seems like there are bigger issues than a 10K LOC file. Unless I’m a complete amateur that thinks they’ve always been not an amateur, and needs an LLM to make a minor change. I just don’t see the point a lot of the times.
What do I do with all this extra time I’m saving? Retire early because I’m getting paid more for doing less right (and I saved all that time)?
How about when the LLM doesnt work right? If I’m a junior engineer that lets a computer write everything for me; How much time do I spend hacking at a prompt to get what I want vs just writing the damn code?