AI is dumb and is not going to rob your work as a programmer.
Expanding on this:
https://devrant.com/rants/12459112/...

Don't know about the others, but programming and IT is mostly safe unless you're a secretary answering to mails pressing 1 keystroke at time with index finger.

Bullshit.

I’ve tried EVERYTHING. As a developer, I know exactly what instructions to give and how to explain them. I tried this stuff for years.

I abandoned the idea to give Ai a full blown workspace to vscode with copilot, even with experimental LLMS (Claude 3.5, Gpt4o, o1, as per my linked post, copilot is dumb as a rock), because it fucks up every fucking time so bad.

I tried getting an AI to build a simple project, something that has plenty of samples of code around, something that I was sure it could have been in its training dataset. A copy of Arkanoid, in HTML/CSS/JS, even reformulating the prompts over and over with different LLMs that claim to have reasoning abilities. I provided detailed feedback step by step, pointed out the errors, improvements, and problems in-depth to: o3, o1, 4o, deepseekv3+R1, and Qwen 2.5 Ultra. I even activated web search and suggested scanning GitHub repos when necessary. I gave examples of code after several failed attempts.

And guess what? Nothing. A total mess. Half the time, the game didn’t even run, and when it did, everything was wrong—bricks overlapping, barely anything working the way I asked. Even though the internet is full of similar code, and I gave it part of the solution myself when it couldn’t figure it out.

Don’t worry, AI isn’t going to steal your job—it’s just a broken toy. Fine for repetitive, simple tasks, but nothing more.

It's years that they make hyped up bold statements that the next model will revolutionize everything and it's years that I get delusional results.

It's just good at replacing some junior bovine work like mapping some classes or writing some loops with not too much variables and logics involved.

Sigh. My error was getting too comfortable using it and trusting/hoping that this ramp up in AI developement would have brought an easier life to dev.

Silly mistake.

Keeping up the tradition!
https://devrant.com/rants/15030806/...

Now powered by the awesome Claude 4!!!! The latest bleeding edge gem in the LLM trend that by the bold claims of big tech and various youtubers is stunning and will replace programmers/insane/godsmacking

This time, I decided to post because I was on the verge of a mental breakdown and I had a firsthand experience and a bit of free time, so instead of waiting that the rage boils down, I just took the chance and so we have a fresh AI experience to proof my previous rants.

Problem:
I have an application that manages interactions between a Mediator pattern between Kafka, some http listeners and other stuff (Rabbitmq, Redis (redis= another shit) etc etc)

Kafka handling was already done, i needed to exacly replicate what was being done with kafka for http. I said, heck, we have AI, it's good to do bovine stupid work, why not let him copy the whole structure, they have also agents on copilot on vs code, and they pulled out Claude 4, let's give it faith again.

Big error.
Beside the havoc the fucking agentic AI not being able to fully copy an already existing pattern and scaffolding, it did half shit wrong.

One of the most frustrating parts, since today I have an example, was this (summarized version of the prompt because I was very much more specific also giving the AI files and pointers to the code and explaining it):

PROMPT:"I have to return fake http transports, just copy what exists for kafka and adapt it to a new transport type called "Http", this is the structure {json with the class}

AI: "I need to see the current ITransportsItemResponse interface first to understand the structure, then I'll modify ...... BLAH BLAH"

Of course I had to review the whole code.

PROMPT:"any valid reason why you dumb shithead didn't respect the IGetKafkaConnectionsItemResponse and generic IGetTransportsItemResponse format and you pulled out of your ass a full blown IGetHttpConnectionsItemResponse with extra properties when compared to IGetKafkaConnectionsItemResponse"

AI: "You're absolutely right, I fucked up. Looking at the IGetHttpConnectionsItemResponse interface, it has way more properties than the basic IGetTransportsItemResponse and IGetKafkaConnectionsItemResponse interfaces. BLAH BLAH wall of text reasoning"

Then it modified the api calls to suit the kafka objects and didn't update any class of the Http transports

PROMPT:"So you tought it was a good idea to leave the #sym:IGetHttpConnectionsItemResponse like it is respect to #sym:IGetKafkaConnectionsItemResponse ? Why? And answer the why don't apologize like a little wuss"

AI: "I left them different because they represent different domain concepts... BLAH BLAH EXPLANATIONS WALL OF TEXT"

Now ai tought it was good to do this and that but....

PROMPT: "In your fucking careful analysis didn't you reallize the "items" object are a basic representation and in the fuckin same folder there is also the object with the full set of properties?"

Literally it missed objects used in the same folder for different scopes and modified stuff without caring.

AI: "You're absolutely right. I missed that there are TWO different response types BLA BLAH"

I won't continue to not get too lenghty than it already is but the point is:

AI IS RETARDED.
People say it will replace programmers.
People says agents are the future.

Sad reality it's an overglorified broken ball of if/else that can't do shit well beside bovine work.

No amount of tutoring it with careful prompts, explainig the code and whatever else is going to fix it.
I've used gpt since gpt 3 and no model has been up to anything good, not even NLP. They suck also at the sole scope they were invented for.

I tried to ask GPT to make a curriculum based on another, I gave it the example curriculum and another one with the informations.

I carefully explained that it must not be a copy of the other, they are 2 different roles and to play by fantasy to make it look it was written by 2 different persons and to not copy stuff from the other.

Hope lost. It looked like the other curriculum was copied over and some words swapped, lol.

What a fucking joke, lmao, I am studying deep learning and machine learning to get on the bandwagon to make my professional figure more appealing, but I can already feel this is a waste of time.