LeafItAlone

I’m confused.

Is your point that programmers are generally worse than plumbers and HVAC installers? People except software to be trash and barely usable, but have higher expectations for plumbing and HVAC?

Some bricklaying may be art. Not all bricklaying is art.

> I miss discussions and debates about architecture and solutions to problems.

If you aren’t having these, then your team is using these tools wrong. AI assisted coding should open you up to more of precisely these conversations. Then use them to implement that.

> only to be passed the modern equivalent of a LMGTFY link hurts in a very particular way

Apt analogy, because if you are asking questions that can be answered with the AI equivalent of a Google search, you are wasting someone else’s time.

> Plumbing pays pretty well

Plumbing does not pay well for the average plumber. Not doctor-well at least, which is what you are responding to.

Can some plumbers make good money? Absolutely. But you need to do dirty, body-breaking work for years.

There’s nothing wrong with being a plumber and it’s a profession we surely need young people to go into. But the pay and trade offs vs a white color job will lean heavily in direction of the latter.

LLMs can provide the intentions of the code they write. To say they can’t is saying that they can’t fix bugs, which they very obviously can do effectively. So, just tell them to write the intention in the way you want it. If you are implicitly providing the direction in the prompt, make that explicit - you then it will have the context for the change while working and for the commit message and you’ll likely get a higher quality output.

Fix your harness. Provide rules, format, and good examples.

You probably had those for the humans in your team for when new hurts join, right? Just direct your LLMs to them and you’ll have a much better experience.

Just like you can’t expect a new junior dev to know what to do without direction, the same applies with LLMs.

A big win of LLMs in my book is the absolute reduction of commit messages with just “fixes” or “updates”. Commit messages have become more meaningful and useful, even if far from perfect.

We have one dev who uses LLMs to write the code, but still commits by hand. Most of his messages are of the type above, and none of them are useful.

This is certainly a problem with out-of-the-box usage. But easily overcome. Spend time updating your harness. This is not a hard problem to solve and there are many helpful guides out there.

We basically took our documented (human) SDLC process and applied it to the relevant harness hooks. Since our SDLC docs talked about what good comments looked like and what to avoid, we basically had the direction for the tools. Opus 5 did throw us a loop and increase the verbosity and decrease usefulness of the text, but refining our documentation cleared that hurdle within about a day.

You need a better harness. LLMs are significantly better at this than humans. Add it as a step in your LLM process and your documentation will always be up to date.

I personally find it unbelievable that you have access to all of the public GitHub projects available and still think the typical developer writes good code.

We’ve been tracking performance and bugs for years. Including commits those bugs were introduced in. So when LLM-generated code started working its way into our codebases, we have the before and after. And even comparing human generated code today with LLM-generated code today.

Depends on the prior state.

For one codebase I work in, LLM written code is noticeably and measurably (we have literally measured it for bugs, performance, etc.) better than what existed before. So the LLM code is a welcome change.

Dude, just be nice and let people have fun. Raspberry Pi’s have made it possible for people to do things they never otherwise would have done! It is pretty amazing!