Are you steering towards AI burnout? Afraid of loosing your job to someone with little programming skills, no aspirations to quality, and a huge Claude account? Disappointed about the code quality in your projects, or worse in “your” own code? This is for you. There are significant and legitimate ethical concerns about frontier LLMs run by big tech companies, these have been discussed at length, I’m aware and agree, this post is not about them. Please don’t mistake me for a pro-LLM techbro. Also: Since people have mistaken my texts for LLM-generated before, I’ll tell you that it is 100% human written without any AI-assistance.

Souls in the Great Machine

There is a great book of this title by Sean Mcmullen that I enjoyed reading as a teenager, and at the first glance it describes the opposite of our situation: A big computer where the individual components are human, and work together to form a calculating unit. On the other hand, LLMs are themselves running on actual computers and pretending to be (super-)humans. At a second glance, story and reality are not so far apart though: Our role in the process of producing software is being degraded slowly from being actors to cogs in a machine. The spec-driven-dystopia is that we just get handed down some spec, hammer it into the LLM, and weep when our tokens run out because a technofeudal lord decided to hand out fewer of them.

As a Haskell programmer, I enjoy writing Haskell. Yes, I like the product we make at work a lot, I like what you can do with my open source libraries, but I really enjoy just the process of expressing my thoughts in this language. I’m assuming this to be true for most of you, and also it not to be true in many other languages, which explains to some amount why enthusiasts of different programming languages have different opinions on how bright or dark the LLM-assisted future is. When I generate code, a lot of that enjoyment is at risk. So, don’t, maybe. I want to keep writing (at least the enjoyable parts of) Haskell programs, and not having to read and review (too much) generated code. At the same time, I want to put those tokens to some good use that doesn’t slowly burn my brain away.

Keep writing code

If you want to keep owning your codebase, you need to keep writing some code. If you let it all be generated, it will turn into an LLM wasteland that only your coding agents can thrive on. So you should keep writing code, otherwise your codebase will eventually be lost. Another reason to keep writing code is to keep being a good programmer. Skills can be lost by not practising, and here the risk is particularly high because there is a really low threshold to giving up your coding work and hand it to an agent. After just a few weeks of not coding and handing everything to agents you’ll notice that you have a hard time returning to coding yourself. LLMs are way worse at producing good, human-readable code than advertised. They are somewhat ok at producing code they themselves later work on exclusively. But I’m sure you’ve already experienced the despair of looking at a completely generated file that must contain a bug somewhere, and your perceived inability as a human to find it yourself, because the landscape is just so alien. So how to get to those productivity gains if not by letting agents do the coding? By making them do nearly everything else. Especially the boring work that is a nuisance to you. Ideally those tasks should be automated away, but you still need to keep your hand in the code to maintain your skills and ownership of the codebase.