Fuck AI

I would actually take it a step further and say it’s worse than useless tbh.

What good is it to have a summary generated about night clubs when literally zero of the details generated can be presumed accurate? Like it will just full on ass pull basic details even down to the hours of operation. This constant confident misinfo actually harms your process.

you were going to go through them 1 by 1 anyway

And furthermore, we’re ignoring the fact that no, you were not. Nobody in the history of time has ever run a detailed comparative analysis on a massive list of nightclubs in their area for the purpose of optimizing their night out. You just look at the map for whatever’s gonna be cheapest to uber to and quickly check the reviews lol. Or more likely someone in your group started out wanting to check out a specific place, and that’s that.

The mere concept of employing AI in this instance was delivered to you by a marketing firm. That’s the bread and butter of these companies: pretending a trivial, routine task that we’ve performed without friction for many years is actually a large project that justifies investment in and deployment of their bloated expensive product.

You can go back and forth with me all day trying to contrive different random examples where you think maaaaaybe the AI saves you ten seconds of time if you squint, but in reality people who often use it just waste a bunch of their time floundering and walk away less informed than when they started

How does the AI know the "best night clubs"?

It just regurgitates, with a level of randomness, the existing user reviews you would have gotten on a search result. Plus AI leaves a ton of opportunity to obscure advertising by influencing the summary output to favor certain locations in a way that is less obvious than ads and search result ordering.

Yeah, it is great at getting an answer that looks plausible as long as you don't care about accuracy. At that point just do a web search for nearby clubs and pick one randomly, the end result is the same except the latter isn't driving up costs and increasing pollution for everyone else nearly as much as AI.

Goggle AI says

first try goggling "night clubs near me"

I actually find the opposite is true. I don't mean it's bad but you get much better results with some basic starting point.

For example at my last company we had a database which for a VERY small example had a table with device serial, test type, test result(pass/fail), and an ID to another table. For each test in the other table there was a series of rows with that id which had all the details of test. For example unit 123 might be circuit board with 5 test points testing voltages at various points, all tested at one test station.

So you would go into table 1, select all lines with serial 123 and test type "electrical test", copy the test ID, go into table 2 and select all results for that ID.

One day my boss sent me a list of 500 serials and told me to pull all the details and present it in a table.

Doing that manually would be hours. So people with some sql knowledge might recognize you could use a sub query. Problem being the list sent to me was just a table copied and sent over teams. Would probably take atleast half an hour to copy that into ssms and correct all the formatting to be valid sql.

I wrote a script that pulled the details for 1 serial using a sub query and pivot the results , copied that and the list of serials into chatgpt and asked it to modify the query to include all the serials in the table in correct sql format. It worked great( I got results for 500 unique serials and a test of a random 10 of them got the same results). It took maybe 5 minutes.

Now trying to get chatgpt to do that from scratch would be painful but with some idea of structure of data, an idea of what I wanted to do and an example to follow it worked wonderfully.