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.

Yes, i like to rant.
Yes I confirm this:
https://devrant.com/rants/13046679/...

Yet they produce bold statements about AI being in the 50 top programmers and shit.

LMAO

I tried vscode copilot insider both normal and with agents up to o3-mini and all other models (gemini, claude, etc)

I just had to do 2 things:

1) Custom angular table component which follows usual angular standards and custom columns are available (button columns, date columns etc). Asked to add an accordion column and test it in a component.
Given other samples from my code and internet.

Totally fuck up. Column never appeared and never worked. Tried to refine prompt and context 10 times each model. Nothing. it just spits shit in the chat console and tries to do backflips in resoning (agent mode) and also in edit mode.

Sometimes it even gets stuck and just goes into edit mode and refuses to modify files and just spits the code in the chat LMAO and I have to reboot vscode to make it work again.

2) Tried some unit tests with jest, given PLENTY of samples of working tests from my code.
Told it to strictly adhere to every syntax, rule and detail it sees in my tests.
Yet it adds unwanted imports, fucks up stuff and invent things.

what a delusional shit

I literally said to myself: "Sigh, I want to believe this shit will relief me from the unbearable pain of dealing with this shit angular code and this utter shit jest crap idiotic framework for testing.
I will allow myself 2 days to waste time on this retarded shit".

2 days wasted, ai = useless and bug shit.

Heck at some point i thought I was unable to write prompts and let another ai write my prompts for me to feed into copilot, but it didn't change anything.
I read an article that said you shouldn't talk "robotic" to ai and you get 10x results and i tried to talk to it like i was explaining to a colleague, then to a kid. Nothing.

Again work is safe. They are years away from making anything really replacing any human programmer with decent experience.

Should I try to build a OS myself with this: https://github.com/danistefanovic/... as my starting point?

My goal is to try and build a Linux OS that can also run Android apks (not necessarily from the Play store) that is imaged and able to run on my Raspberry Pi. Or this is a dream that cannot be realized?