Technology

Thanks OOP for putting words on what I've been feeling for months.

Were "incentivized" (read "threatened into") pushing features quicker than humanly possible with no regard for quality, sustainability and proper ownership of the code to please one (1) stakeholder who had a barely thought out idea. The amount of tech debt in staggering, broken features come and go as the code is "rewritten" with each commit.

It's completely unsustainable and the only ones who profit from it are the LLM providers. When the whole product collapses, the only one to suffers the losses are the company building that product and their clients. Their employees get fired because it's somehow their fault. LLM providers get even richer because now the remaining employees burn through tokens to try and "fix" millions of nine of code nobody has ever thought out, written and reviewed.

Companies pivoting to "full AI" code are literally committing suicide, for the exclusive benefit of LLM providers. I get that that's Anthropic's and OpenAI's plan all along. I just can't understand the utter stupidity, hubris and amount of kool-aid drinking most CTOs are riding right now.

I have yet to see a developer endorse LLM output in an area they are able to do useful work in.

Either it is someone who thought the LLM helped them write unit tests, and it's never tests that capture the intent of the code, because they don't know that is important. They see tests as "this stuff I have to add for process reasons".

Or it is an LLM helping them write a fade-in tooltip with 200+ lines of React Javascript, because they don't know this is a one-line CSS rule.

Or have the LLM add code documentation that does nothing but repeat the function signature, because they don't understand they need to empathize with the person using of maintaining the functions. Write something that helps jump a non-obvious gap, or write nothing.

Or have the LLM do code review because they think it's about obsessing over syntax, not about discussing how the change applies to the intent.

Or have the LLM write their pull requests because they think it's a boring process thing that summarizes the change, and not a discussion of the purpose, intent, cost, value and approach of the change.

Moral: If you think LLM is good at X, it's because you really really suck at X, and you need to get better at it instead of pumping out shit work faster while learning less.