Gniewomir Świechowski

When doing AI-assisted development using agents, your prompts will inevitably have a lot of decision gaps. Sometimes the model’s “defaults” used in those places are fine, but leaked system prompts suggest that most of them are explicitly prodded towards the lowest change-surface solutions. It’s a safe choice, but in a mature codebase, this will become increasingly corrosive with each change. In fresh projects, it will lock in place bad design decisions that you or the agent made early on. ...

Separating domain entities from ORM models is often dismissed by developers and managers as ‘over-engineering’. Yet, long ago I lost count of how many times a promised ‘simple CRUD’ app turned out to be neither simple nor CRUD. It was just hard to reason about, because the ORM models had outstayed their welcome as a proper domain substitute. 1. The Write vs. Read Symmetry Fallacy The ORM creates a false impression that writing and reading data to and from persistence are the same responsibility. Yet, we care about correctness when writing and performance when reading. There is no symmetry here. ...

This list started as an idea for a short LinkedIn post, but ended as a summary of systemic problems that need to be addressed to make coding LLMs/AI Agents a paradigm shift in software engineering—not a dead end that creates as many problems as it solves. Perhaps this attempt to organize my own thoughts on the topic will be of some use to anyone. Misunderstanding of intelligence: LLM-based agents do not reason in the human sense of the word; but are very advanced prediction and pattern recognition engines—which defines their unavoidable limitations inherent to the transformer architecture. Contrary to the marketing, they are not “intelligent” - defined here as the ability to generalize, abstract, and establish causal relationships between facts. They just simulate this process very convincingly using language as a medium - being a “Stochastic parrot”1, constrained by both training and syntax to the benefit of prediction accuracy - especially in the context of programming. ...

As AI-driven existential dread spreads among software developers across the world, I’m watching reactions varying from the shit-eating grins of those convinced that we must repent for tech-bros’ arrogance, through the crazy-eyed prophecies of the new golden age, and finally, smug assertions that the phrase “software developer/engineer” will at last regain its true meaning. Because most of us just glue stuff together and are nothing like the giants of prior glorious ages. ...

On how the industry really would like to replace sycophantic developers with sycophantic developers armed with sycophantic AIs and how it will amplify already existing dysfunctions. Again. ...