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.

I will not miss you bitch. See screenshot. I received new hardware. I will use a laptop with good specs as server. My dad bought it from his previous employer because he went for retirement. It has an ultrabook-grade 11th gen processor and he only bought it for 350,- euro. His former employer was a school, they don't give a fuck about money like a commercial company would do in such case. It's originally bought with tax money anyway.

https://llm.molodetz.nl is currently online but not for long, i hope to have smth running at end of the weekend. Probably a 7b model. I have plans with it that require some performance so I won't use the heavy ones.

Retoor1b currently is 0.5b or 1.5b. I forgot. The models with lower parameter count are a bit more naive and trainable like a kid. They're also not very biased yet. So, that will be my main new challenge. How to make a chat bot unethically human. No political correctness under this roof.

Would be nice if i could make it a bit like bratgpt. Sounds like a joke, but that model is expensive as fuck. You'll be shocked. But i would like to implement some sarcasm in it. A bit unpredictable. But normally such configuration escalates into very weird behavior.

My 'server' has a freaking 4K screen and i'm working on a decade old laptop. But seriously, the keyboard of the new one sucks. Nothing beats a x270. * tik tik tik * rakketakketak *. My previous x270 missed four keys. The three x270's i had, all had familiar experience but still different. The other two would never lose a key I guess. I configured the new 'server' that it safes battery, configured for mostly on AC.

I'm living on limited amount of cash (and will work again when i will run out). That's why i normally don't spend money myself on such things. So i'm now very happy. Fuck, this was about to be rant about how much my AI sucks but it ended in happy stuff. Oh well...

If you're still reading, you're the best!

Edit:
Images uploading broke again. Here is link: https://devrant.molodetz.nl/llm.png

It's that time again because it needs to be remembered
https://devrant.com/rants/13347344/...

AI IS FUCKING RETARDED.
I would literally be ashamed to be one of those multibillionaire companies giving out trash or be ashamed to be recognized as someone which invested in it.

Jesus.

I tried out every model, local and online.
It's fucking trash for anything more than a preschool special kid could do.

I literally had it to code and it can't do anything beyond basic code without the need for me to supervise everything and patch this disaster everywhere. It feels like having that dumbass junior just arrived doing code and having to review every line because it could contain a death trap.

I tried to make it do a dieting plan.
I literally gave it everything.
Macros, kcal, a restricted list of 15 foods and asked to do some bulk cooking list to make the diet later.
It can't do basic math to figure out macros and not only, it fucking halluicinates like a crazy LSD druggie even doing a few lines of that shit.
It literally invents calories counts, macros and shit out of his stupid ass.

I tried literally to bring it by the hand in doing the tasks and it still fails.

You might say: Hey it's a "Language" model.

No, it doesn't matter. Amy discussion besides hi dumb fuck how are you soon turns into an AI mind trip where it churns and repeats stupid stuff.

No, it won't replace anyone anytime soon.
It's just a fucking joke