DEV Community

Cover image for The AI development trap that wastes your time

The AI development trap that wastes your time

Samuel-Zacharie FAURE on October 30, 2025

Have this ever happened to you? You are asking your AI agent to develop something, correct a bug, or whatnot. It's currently completely lost. You...
Collapse
 
mikeydorje profile image
Mikey Dorje

The real gain of Al is in the cognitive load reduction.

💯

Collapse
 
canro91 profile image
Cesar Aguirre

Great point about cognitive load.

Do I understand exactly the specifications I'm trying to implement, or the bug I'm trying to solve?
Do I have an exact plan for implementing my changes?
What is the current abstraction level to which I should be prompting now?
Which other information am I lacking?

These four questions made me think AI is helping us rediscover coding.

Now AI agents/bots/chats are forcing us to follow a process to get better result from the tool. But these four questions have been true all this time: understanding what to write, coming up with a execution plan (even if that's outlining a solution with comments), decomposing a problem into smaller ones, and ask clarifying questions. That's coding since the beginning of time.

Great piece!

Collapse
 
smyekh profile image
Smyekh David-West

These are great points!

I’ve come to realise that if the AI seems lost, it’s often a reflection of the user being lost as well. Barring, of course, the occasional day it decides to hallucinate. And don’t we all have our off days?

The advice to "take some time to think about your implementation plan," particularly rings true. Too often, we begin prompting without a concrete strategy, simply hoping the AI will grasp the gist of our problem and deliver a solution.

I agree that prompts must be premeditated. I find it effective to state the primary goal in the initial query to set the tone and establish a shared context. This ensures we are on the same page from the start. Ultimately, the session's context and your own clarity on the problem are the most critical components for success.

Collapse
 
netnavi profile image
Ahmad Firdaus

WHen using AI, I often start it from determining how the project should be done.
brainstorming the ideas, creating project check point as control, and code assist to prevent typo and etc. AI also helpful to create project log and raw documentation for speed reading.

basically we are who choose what AI to use and what for. its good for creating a frame and draw sketch, but the finished products is depend on our personal touch.

several tries with high level prompting, AI have tendencies to repeat the same mistake over and over. or sometimes hallucinating with a job that not needed, once the AI cannot find a file, but the file is there, just because the text formatting is not usual like utf-16. its cycled for few times before its finally give up, and then voila STackoverflow have the answer.

Collapse
 
devloic profile image
Loic Devaux

I experienced those cycles many times. If I can't suggest the AI an alternative approach I will restart the AI with a new context... but sometimes insisting pays out and task are resolved after 7 to 8 debugging cycles so it's really difficult to take the decision to "reset". I think this situation will evolve once AI will be able to make autonomous tests with different kind of systems, for example for web apps with the chrome devtools mcp , these tools can give the ai the extra insights it needs. I think we are not far away of having AI directly in the runtimes, feels like Tron.

Collapse
 
dingowashisnamo profile image
Jeremy Strong

I have a few ways of approaching this. Often when stuck in this cycle in indicates that there's something wrong with the architecture. Its not simple enough. It doesnt flow right. When the AI cant write tests, its an indication of the same thing.

I generally start with that, ask the AI if the overall approach is right. WHY are we stuck? Help me rewrite it. Dont try to save lines of code, spend them for simple reasoning.

Another approach I use is to build a simplest possible template that represents the logic I'm trying to implement. I used this when troubleshooting a nested drag and drop feature. I went round and round inside the application code. Every time I went round, the ai lost sight of anything but the problem and broke something.

So I had it build a simple, isolated template. Got that working, and had it refer to the template to fix my main logic.

Both of these approaches work. It can feel like you're losing progress because you aren't attacking the problem you see. the squiggle, the failing test. But taking a step back lets you reason around the problem.

Collapse
 
wizardzeb profile image
Zeb

This is why I do not vibe code. It's just not healthy. I try to use AI as a thinking partner not a servant. If the AI starts to spiral I go back to old fashioned Googling or using the debugger. Use your brain people!

Collapse
 
shemith_mohanan_6361bb8a2 profile image
shemith mohanan

Brilliant insight 👏 — loved the reminder that AI’s real value is in reducing cognitive load, not just speeding up work.
The “sunk-cost prompting loop” part hit hard — and that closing line, “Be the master of your AI, not its servant,” is gold. 🔥

Collapse
 
parag_nandy_roy profile image
Parag Nandy Roy

Love this take ....AI isn’t a speed booster....it’s a mental load reducer...

Collapse
 
jlhfr profile image
JLHfr

I'm still very new in the dev space. But one of the first things I realized, as many of you mentioned already: AI isn't a reliable source if you don't understand the code by yourself. It only adds more confusion to the whole process, if you think you can rely on it completely.

Collapse
 
samuelfaure profile image
Samuel-Zacharie FAURE

As usual, comments are welcome <3

Collapse
 
bhadreshkumarghevariya profile image
Bhadreshkumar Ghevariya

I have not done programming recently and just stared from basics again. It is good to know that I can’t rely on AI to code solution for me before I myself understand it. Will save me lot of time.

Collapse
 
fabienmartin profile image
Fabien • Edited

I had a very odd experience with Codex recently where it could not make the specific changes I was asking but was trying to gaslight me about the specification of the APIs I wanted to use. Even when given the documentation, it will recognize the documentation and move back to its previous gaslighting & refuse to make changes.

But I could only detect this because I knew very well the APIs and docs. Wonder what would happened if it was something I was not familiar with!

I think the sunk cost fallacy is really what it is as you pointed out. I think after a few experience of circling around for hours with AI, it's easier to notice.

Collapse
 
a-k-0047 profile image
ak0047

Thank you for sharing this article!
I'll keep it in mind.

Collapse
 
louis7 profile image
Louis Liu

Great points!

Collapse
 
neurolov__ai profile image
Neurolov AI

thoughtful take

Collapse
 
dejiowoeye profile image
OWOEYE AYODEJI

I strongly agree, as a programmer, AI is only a tool for cognitive load reduction.

Collapse
 
kosmickroma profile image
Kory R Karp

Love this you are absolutely right, I have been learning this the hard way.

Collapse
 
pravileaf profile image
Praveen Kumar

It's a word of millions. Great insight.

Collapse
 
provenco profile image
Proven

Like. this App!

Collapse
 
mr1mmdrza profile image
Mmdrza

When you gradually hand over daily and small tasks to the Ai model, we are gradually keeping our brain from working and making it lazy, this will continue until you turn from a highly professional and busy programmer into an editor and make your brain lazier and lazier every day that your hands will no longer have the desire to go to the keyboard.
The brain is exactly like your own body. If you exercise every day, you will have a healthy life and without physical problems and you are always ready to do the same. What happens in the opposite case?!!

Collapse
 
samuelfaure profile image
Samuel-Zacharie FAURE

Eh, I might agree if one stopped using their brain completely to use AI

But most jobs will require that you still exercise your brain and let AI do the less intellectual parts of the code