Re:Replacing a SQL analyst with 26 recursive GPT prompts
by freejazz on Wednesday January 25, 2023 @10:53PM
(#34527490)
But, generally and unless there is a glaringly wrong result, only an analyst is going to know if the bot is right or not... what exactly does that gain you?
Re:Replacing a SQL analyst with 26 recursive GPT prompts
by catothedev on Wednesday January 25, 2023 @10:58PM
(#34527518)
It gets you a really sophisticated 'auto-complete' feature
Re:Replacing a SQL analyst with 26 recursive GPT prompts
by freejazz on Wednesday January 25, 2023 @11:23PM
(#34527658)
Not really. I'd guess that most people can tell if auto-complete is providing the answer they "wanted".
Re:Replacing a SQL analyst with 26 recursive GPT prompts
by kqr on Thursday January 26, 2023 @12:53AM
(#34528135)
Maybe it's not a position where it is critical that all answers are 100 % accurate. Maybe getting it right every once in a while is enough to pay for the GPT compute time, but not really for analyst time.
Re:Replacing a SQL analyst with 26 recursive GPT prompts
by anentropic on Thursday January 26, 2023 @05:37AM
(#34530051)
Seems like the issue would be you'd generally get results that 'look' right but would never know if they were actually right without going through and... analysing them
Re:Replacing a SQL analyst with 26 recursive GPT prompts
by kqr on Thursday January 26, 2023 @09:29AM
(#34531970)
I'm saying there are applications where you don't have to know! As long as the fraction incorrect is less than 50 % and you have 2:1 odds on the consequences you don't have to know which 50 % are incorrect.
Re:Replacing a SQL analyst with 26 recursive GPT prompts
by freejazz on Thursday January 26, 2023 @10:10AM
(#34532562)
Really? Then why pay for the thing in the first place. Why keep the data and make the queries if the results don't actually matter? I'm impressed that you have the ability to envision such a possibility, perhaps you can use that ability to come up with something reasonably likely as opposed to "conceptually possible".
Re:Replacing a SQL analyst with 26 recursive GPT prompts
by kqr on Thursday January 26, 2023 @10:59AM
(#34533400)
I'm trying to think of easy examples. You're right that none obvious come to mind. I'm sure there is a sweetspot where we can make more money from cheap-but-sometimes-wrong GPT queries than paying for an analyst to be more definitively correct, but I'm tired and a bit fuzzy on the exact parameters.
I'll continue to think about it and write something up!
Re:Replacing a SQL analyst with 26 recursive GPT prompts
by freejazz on Thursday January 26, 2023 @12:07PM
(#34534627)
Hard to imagine a business model where you sell that data that is only right 60% of the time. Maybe in a world where the other best data is even less reliable.
Re:Replacing a SQL analyst with 26 recursive GPT prompts
by moonchrome on Thursday January 26, 2023 @08:04AM
(#34531138)
If you're OK with garbage data you don't need ChatGPT - you can probably make up plausible data on your own. Unless you're building some lorem ipsum stuff.
This all assumes that the bot doesn't need tweaking for every answer — i.e. it gets at least some answers right without needing modifications to the bot — which appears to be the case based on the examples in the post.