They can be worse than worthless. They can sabotage your work if you let them making you spend even more time fixing it afterwards.
For an example. I've used Gpt4 as a sort of Google on steroids with prompts like "do subnets in gcloud span azs" and ", "in gcloud secret manager can you access secrets across regions". I very quickly learned to ask "is it true" after every answer and to never rely on a given answer too much(verify it quickly, don't let misinformation get you too far down the wrong route). So is it useful? Yes, but can it lead you down the wrong path? It very well can. The least experience you have in the field the easier it will happen.
>You just cannot expect it to ship a full programm for you, but for generating functions with limited scope, I found it very useful
Entire functions? Wow. I found it useful for generating skeletons I then have to fill by hand or tweak. I don't think I ever got anything out of Gpt4 that is useful as is (maybe except short snippets 3 lines long).
However, I found it extremely useful in parsing emails received from people or writing nice sounding replies. For that it is really good (in English).
But that is the same, when you blindly follow some stackoverflow answer.
And yes, I always have to tweak and I use it only rarely. But when I did, it was faster than googling and parsing the results.
The amount of fighting I needed against MS development tools mingling my code recently is absurd. (Also, who the fuck decided that autocomplete on space and enter was a reasonable thing? Was that person high?)
I basically gave up on llms because i was spending more time figuring out what it did wrong than actually getting value.
People without programming skill are still impressed by them. But they yet have to learn or deliver anything of value even with the help of chat bots.
Here's the transcript (it pre-dates the ChatGPT share feature): https://gist.github.com/simonw/1aa4050f3f7d92b048ae414a40cdd...
I wrote more about it here: https://simonwillison.net/2023/Apr/15/sqlite-history/
Here's another one I built using AppleScript: https://github.com/dogsheep/apple-notes-to-sqlite - I wrote about that here: https://til.simonwillison.net/gpt3/chatgpt-applescript
Also: not every system has to be a scalable system. That's another lesson junior engineers (should) learn.
LLMs do produce impressive code. Even if they were indeed just procedural generators it would still be impressive. The code has structure and appears useful.
But the issue is that you can tell it makes no sense, there is no thought process behind it. It fits in no greater picture.
Even if you add more context it still has no purpose.
People that find this useful are the same type that copy stackoverflow code that they dont understand. It kinda works when it does but again it doesnt fit in the bigger picture.
Code isnt about spelling instructions - an…ai can do that - code is about what goes where in a way that the what changes as often as the where. It’s the bigger picture. So yes it can help and replace those that spell instructions but it will be hard to replace those that are required to deliver more.
Completely agree with you. That's my job. The LLM is effectively my typing assistant.
Even this can be a big time saver, that increases productivity.
Just like others have said, it isn't going to write a Pynchon novel, but it does do a great job at the other 99% of general writing that is done.
Same for computers, the average programmer isn't creating some new Dijkstra Algorithm every day, they are really just cranking out connecting things together and doing the equivalent of 'generic boiler plate'.
I've had mixed experiences with getting it to generate new code. It produced good node.js command line application code. It didn't do so well at writing a program that creates 16 bit PCM audio file. I asked it to explain the WAV file format and things like lengths of structures got so confusing I had to research the stuff to figure out the truth.
It's been hit or miss with rust. It's super helpful in decrypting compilation errors, decent with "core rust" and less helpful with 3rd party libraries like the cursive TUI crate
Which comes as no surprise, really, as there's certainly less training data on the cursive crate than, say, expressjs
Also FWIW I have actually pointed it at entire git repos with the WebPilot plugin within ChatGPT and it could explain what the repo did, but getting it to actually incorporate the source files as it wrote new code didn't work quite so well (I pointed it to https://github.com/kean/Get and it would frequently fall back to writing native Swift code for HTTP requests instead of using the library)
And for text I know people who use it succesfully (professionally) to generate texts for them as a summary from some data. They still have to proof read, but it saves them time, so it is valuable.