- cross-posted to:
- nyt_gift_articles@sopuli.xyz
- cross-posted to:
- nyt_gift_articles@sopuli.xyz
A radio station in Poland fired its on-air talent and brought in A.I.-generated presenters. An outcry over a purported chat with a Nobel laureate quickly ended that experiment.
In fairness, about 50% of my code by lines is written by AI these days, and I don’t have it linked into my code base. That claim isn’t ridiculous
Now, of that 50% is 88% long repetitive crap that I could easily write but find mentally draining, the other 10% is something simple that I would normally copy paste from elsewhere because I forgot the exact syntax (and don’t exactly remember where I used it last) and me giving it a shot with things I don’t want to do, like restyling a page. The last 2% is me giving it a shot with business logic for shits and giggles, occasionally I’ll try to coach it through the solution but usually I just grab bits and pieces and rewrite it myself
Granted, this is the easiest and most simple and repetitive code, but it’s still a godsend. Now can AI write the other 50%? With a proper setup where it ingests the code base into a vector store it might get up to 75%, if I was willing to coach it through my tasks carefully (taking more time than the task would take me) I could probably get it up to 85% or 90%, but that last 10%? It just can’t, it’s not even close
It’s not taking my job without a paradigm shifting breakthrough or two on the scale of “all you need is attention”. Even then, it only works if you write your prompts like code… If you don’t understand how to use it and understand the code well enough to communicate the goal explicitly and unambiguously, you’re not going to be able to drive it where you want it to go
To put it another way, you can build 90% of the system in 10% of the time it takes to complete the last 10%
I have access to AI integrated with my IDE. It mostly guesses at the line I’m going to write. It probably gets it right 50% of the time.
It also very, very often suggests stuff that works but isn’t very good. Like it offered some convoluted suggested for adding audit fields to Firebase. Ultimately it did suggest the solution I went with, but only after starting down the road of stupid ideas.
Like, if your code base is pretty good and you just need to tweaks stuff that is already good enough that’s one thing. I frequently look at the code base and wonder if it was implemented by someone who really knows Java at all.
I suppose it might be fair to assume a huge technology company would have their shit together, but technically I work for a huge tech company… just not the same core business. Tech enough that we have a whole mess of internal AI tooling to create AIs for specific things.
We can create an AI agent, but we can’t follow simple fucking rest standards.
Anyway it’s hard to quantify, but I get less mileage out of integrated AI tools than I do bouncing ideas off ChatGPT.
I think that’s fair.
I don’t have AI integration in my ide, mostly by choice -if I pushed for it I could make it happen, but I just don’t think that’s a good idea at this point
AI can be a crutch . One that limits you to the level of a baby developer. If you can’t effortlessly understand what it gives you, frankly you shouldn’t be using it.
Bounce ideas of chat gpt. It sounds like you’ve got the right idea - your reaction sounds correct to me, you should never ever trust it… You must only use it, and that’s the tone I get from your post.
It is a tool, you are a programmer. You exploit tools, you do not trust any tool. You are the one who turns ideas into actions, never forget that and you can use this new tool anywhere it makes your life easier