In the 1980s, economist Robert Solow made an observation that reminded economists of today’s AI boom: “You can see the computer age everywhere but in the productivity statistics.”
I’ve used AI plenty of times to help troubleshoot some weird error message. Sometimes just an old-fashioned Google just isn’t enough. There needs to be added context, which would just screw up the Google results.
I treat talking to AI for advice (in any category) roughly the same as asking an IRC channel…because that’s basically what it is. It’s taking in data from tons of sources and summarizing it.
Some of those sources might be legitimate and knowledgeable, some of them might be a negative-scored stack overflow comment.
If you have no domain-specific knowledge, you won’t know how to identify an issue in its response, and you shouldn’t be blindly copying code. Trust…but verify.
ETA: another example, just now…I was having trouble getting a specific response from a REST API in Ansible. As it would turn out, doing the lookup with REST would require at least two separate lookups to get what I wanted.
The agent suggested I try using graphql queries instead. I’ve never used the graphql API before…tbh I was slightly intimidated by it. But the agent gave me an example for what I was looking for…and after changing the formatting around a bit it kinda “clicked” for me. I asked for an ELI10 on graphql and I definitely learned a bit from it and will be using this (graphql) more in the future.
I’ve had many instances of that, where I’m deep in the weeds and the robot pulls me out and shows me the flowers. Of course…the opposite has happened, too, and the robot finds a rabbit hole among the weeds and keeps shoving me down it.
It’s also been a good rubber duck, even without hitting send. Start typing out the problem and then have an “aha!” moment.
You know…this.
I’ve used AI plenty of times to help troubleshoot some weird error message. Sometimes just an old-fashioned Google just isn’t enough. There needs to be added context, which would just screw up the Google results.
I treat talking to AI for advice (in any category) roughly the same as asking an IRC channel…because that’s basically what it is. It’s taking in data from tons of sources and summarizing it.
Some of those sources might be legitimate and knowledgeable, some of them might be a negative-scored stack overflow comment.
If you have no domain-specific knowledge, you won’t know how to identify an issue in its response, and you shouldn’t be blindly copying code. Trust…but verify.
ETA: another example, just now…I was having trouble getting a specific response from a REST API in Ansible. As it would turn out, doing the lookup with REST would require at least two separate lookups to get what I wanted.
The agent suggested I try using graphql queries instead. I’ve never used the graphql API before…tbh I was slightly intimidated by it. But the agent gave me an example for what I was looking for…and after changing the formatting around a bit it kinda “clicked” for me. I asked for an ELI10 on graphql and I definitely learned a bit from it and will be using this (graphql) more in the future.
I’ve had many instances of that, where I’m deep in the weeds and the robot pulls me out and shows me the flowers. Of course…the opposite has happened, too, and the robot finds a rabbit hole among the weeds and keeps shoving me down it.
It’s also been a good rubber duck, even without hitting send. Start typing out the problem and then have an “aha!” moment.