Grief and the AI split

But there is a price to pay: the code that you generate is not the code that you understand and when things go pear shaped you will find that that deterministic element that made compilers so successful is missing from code generated from specs dumped into an AI. If you one-shot it you will find that the next time you do this your code may come out quite different if it isn't a model that you maintain. It may contain new bugs or revive old ones. It may eliminate chunks of the code and you'll never know and so on.

There is a reason that generated code always had a bit of a smell to it and AI generated code is no different. How much time do you spend on verifying that it actually does what's written on the tin?

Do you write your own tests? Do you let the AI write the tests and the code? Are you familiar with the degree to which AIs can be manipulated to do stuff that you thought they weren't supposed to? (A friend of mine just proved this to his boss by bribing an AI with a 'nice batch of pure random data' to put a piece of unreviewed code into production by giving itself the privileges required to do so...)

The thing about AI is that you don't have to use it for everything. Like any other tool you can use it as much as you'd like. Even though I like the craft, I find myself really enjoying the use of AI to do things like boilerplate code and simple tests. I hate crafting verbose grunt work, so I have AI do that. This in turn leaves me more time to do the interesting work.

I also enjoy using AI to audit, look for bugs, brainstorm, and iterate on ideas. When an idea is solid and fleshed out I'll craft the hard and interesting parts and AI-generate the boring parts.

We all have different thresholds for what is acceptable, and our roles as engineers typically reflect that preference. I can grind on a single piece of code for hours, iterating over and over until I like the way it works, the parameter names, etc.

Other people do not see the value in that whatsoever, and something that works is good enough. We both are valuable in different ways.

Also, theres the pace of advancement of the models. Many people formed their opinions last year, and the landscape has changed a lot. There’s also some effort requires in honing your skill using them. The “default” output is average quality, but with some coaxing higher quality output is easily attained.

I’m happy people are skeptical though, there are a lot of things that do require deep thought, connecting ideas in new ways, etc., and LLMs aren’t good at that in my experience.

There are some studies about maintaining attention over longer periods of time when there is no action required. It will be difficult to keep that up forever so beware of review fatigue and bake in some measures to ensure that attention does not diminish over time.