I love PowerShell but I use it so infrequently that I’m constantly relearning the syntax.
If I need a quick script to scrape date from a system and update a runbook, asking ChatGPT to give me a PowerShell command that pipes the output to excel saves me hours.
For writing small simple functions in an unfamiliar language, it is an absolute godsend. Makes IT way easier.
There’s one other use case I love - i ask it to interview me or challenge me on my ideas. It can sometimes ask questions that cause me to rethink things. But in the end, I’m still the one doing the work. It’s my advanced rubber duck.
Though then have to be careful. I had a requirement to implement a security feature in an unfamiliar language. I gave it a shot and upon reviewing the output, if the code had worked as it wrote it, then it would have had a gaping security hole a mile wide making things worse than they already were, and the bit needed to implement the security was a waste of time. In this case, two wrongs made a right, as it also hallucinated some functions that didn’t exist so the code wouldn’t have even built.
I can see LLM integrated into the IDE maybe providing a quicker entry to some very obvious logic, but it’s a careful UI consideration in terms of balancing offering helpful capabilities versus making the user undo a bunch of times when it was in fact not helpful.
This is just Advanced Intellisence, something Visual Studio already supports. And again - that’s totally fine. I appreciate an occasional “Did you realize you don’t actually use that declared variable anywhere? Here, let me make that code more legible for you.” coding assist.
But you’re not getting an end-to-end automation of a Full Stack Development job and it was crazy to think you would.
Note that I would imagine it as a bit more, like recognizing a pattern where you are going to want to iterate over some iterable and do something super common, I could see an LLM managing to do that better than something like current code completion solutions can. Could also extend it in ways not normally feasible. For example, use something like golang and the IDE can do crazy amounts of completion because so much is specified. In a more loose scenario like javascript or python, the traditional approach can do… some, but a lot more gaps appear since things are too open ended for those approaches to work.
The thing I cited was like a 12 line function that I figured it would get right. But it failed and hallucinated. I had to resort to like result 7 or 8 in an internet search before someone offered a correct solution, so it’s still matching my LLM experience so far, not any better than blindly clicking the first search result and hoping for the best. It can handle some token swap out compared to a traditional copy/paste, but ultimately you are best served by finding the most well maintained library to offload if it’s not something you really need to write yourself.
Yeah, if used correctly it’s awesome. You have to be proficient enough in what you do to catch its bullshit though.
Currently getting back into coding and learning Python syntax. It’s awesome for that, however there also has been a few moments when it confidently wrote complete bullshit.
It’s basically like a talking, semi context-aware search engine. Don’t make it generate big stuff though.
![AI [Saturday Morning Breakfast Cereal]](https://www.smbc-comics.com/comics/1740504999-20250225.png){kind=link}
I love PowerShell but I use it so infrequently that I’m constantly relearning the syntax.
If I need a quick script to scrape date from a system and update a runbook, asking ChatGPT to give me a PowerShell command that pipes the output to excel saves me hours.
For writing small simple functions in an unfamiliar language, it is an absolute godsend. Makes IT way easier.
For anything else it’s worthless.
There’s one other use case I love - i ask it to interview me or challenge me on my ideas. It can sometimes ask questions that cause me to rethink things. But in the end, I’m still the one doing the work. It’s my advanced rubber duck.
Though then have to be careful. I had a requirement to implement a security feature in an unfamiliar language. I gave it a shot and upon reviewing the output, if the code had worked as it wrote it, then it would have had a gaping security hole a mile wide making things worse than they already were, and the bit needed to implement the security was a waste of time. In this case, two wrongs made a right, as it also hallucinated some functions that didn’t exist so the code wouldn’t have even built.
I can see LLM integrated into the IDE maybe providing a quicker entry to some very obvious logic, but it’s a careful UI consideration in terms of balancing offering helpful capabilities versus making the user undo a bunch of times when it was in fact not helpful.
This is just Advanced Intellisence, something Visual Studio already supports. And again - that’s totally fine. I appreciate an occasional “Did you realize you don’t actually use that declared variable anywhere? Here, let me make that code more legible for you.” coding assist.
But you’re not getting an end-to-end automation of a Full Stack Development job and it was crazy to think you would.
Note that I would imagine it as a bit more, like recognizing a pattern where you are going to want to iterate over some iterable and do something super common, I could see an LLM managing to do that better than something like current code completion solutions can. Could also extend it in ways not normally feasible. For example, use something like golang and the IDE can do crazy amounts of completion because so much is specified. In a more loose scenario like javascript or python, the traditional approach can do… some, but a lot more gaps appear since things are too open ended for those approaches to work.
The thing I cited was like a 12 line function that I figured it would get right. But it failed and hallucinated. I had to resort to like result 7 or 8 in an internet search before someone offered a correct solution, so it’s still matching my LLM experience so far, not any better than blindly clicking the first search result and hoping for the best. It can handle some token swap out compared to a traditional copy/paste, but ultimately you are best served by finding the most well maintained library to offload if it’s not something you really need to write yourself.
Yeah, if used correctly it’s awesome. You have to be proficient enough in what you do to catch its bullshit though. Currently getting back into coding and learning Python syntax. It’s awesome for that, however there also has been a few moments when it confidently wrote complete bullshit.
It’s basically like a talking, semi context-aware search engine. Don’t make it generate big stuff though.