> 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.
I wish! We put on a show for a while with tech spec reviews, but the specs were all AI slop. Now we don't even do that. Folks just work in their silos. I mostly learn of new functionality when I am assigned a code review. My feedback on those reviews is passed to an agent.
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.
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.
I think that the idea of generating a commit message based on the content (diff) of the commit is fundamentally wrong.
Even before coding harnesses become mainstream, a lot of tools offered to automatically generate commit messages based on the diff (I think JetBrains IDEs started to offer it very early) and I always cringed when I've seen it.
The reason why I don't like diff-base commit messages is because they are redundant. If I want an LLM-generated summary of the diff, I can easily generate it myself, there is absolutely no reason to put it in the commit message.
What I would like to see in the commit message is some additional context that is not a part of the diff. I don't need to read what has changed, because I can already can see it in the diff (or get an LLM to summarize it for me). But I often do need to understand why this change was made. What were they trying to achieve? That's the important part that is not contained in the diff itself. And this is the part that diff-base commits rarely contain.
I think that even something simple like a link to a Jira (or other bugtracker ticket) is much more helpful than diff summary. Maybe instead of "fix" or "update" you could write just a couple of words about what are you trying to fix and why does it need updated. Still better, than a diff-summary.
This is why, if you have the agent generate the commit message at all, it has to be the same agent that wrote the code, in the same session.
I usually have it lead with a paragraph or two of context on why the change was made (though I often use it as just a tool to turn my rambling on that question into proper English), followed by a couple paragraphs of "abstract" explaining the change (because an LLM-generated summary reviewed by the person who made the commit is better than something which the person reading can get themselves).
I don't see how that would improve the situation? If I do it with the same agent/same context, it tends to just report what it did. Which is the diff, repeated in prose.
The agent is usually told why it was making the change (I at least tend to start my prompts with a description of the problem we're solving), so, if prompted correctly, it can lead with "there was a bug, we root-caused it and here's what the root-cause was", then explain what the fix entailed.
> But I often do need to understand why this change was made.
This is the reason (and IMO the only reason) code should be commented. The why can often be hundreds of characters explaining technical limitations at the time, business considerations, or even just "we know this will break in a non-trivial number of instances but it's an incremental step forward to our end goal so we're just doing it."
I'm not sure that Claude's "Realigned the shape of the load-bearing ownership gate to reduce the blast radius of the design contract; confirmed, not assumed" is more meaningful than "fix".
> I'm not sure that Claude's "Realigned the shape of the load-bearing ownership gate to reduce the blast radius of the design contract; confirmed, not assumed" is more meaningful than "fix".
For PR/commit descriptions, I mainly use Claude Sonnet 4.5. It isn’t perfect, but it produces significantly less of this weird gibberish than 5.x models or even Opus 4.x do
I also use an iterative process in which it writes the description, I read it, and then either manually edit it or ask it to make changes
I use Astra at Very High, and shit is still bad. It doesn't actually understand anything, so it often says things which are clearly not needed to be stated. Recently, I've learned that I have very high standards for these things. For example, "fixes" as a commit msg just is NOT acceptable and would never fly where I work.
A few things, but generally more chain of thought before generating a response. So the model is tuned to think more. Given that what it outputs for this task is a summary of its thinking, tuning it to think more will just make a more verbose, less useful commit message.
Tune your model parameters to what is right for the task, not the highest you can afford.
Astra is such a mixed bag. It makes some amazing reviews and sometimes architecture suggestions that I like. But it’s also lazy and will just make up things.
Have another model (or even another instance of the same model) review the output of the first.
Models will hallucinate. They are also quite good at spotting hallucinations in other models' output (with some more hallucinations thrown in). With a threshold for confirmation, and a few iteration loops, you arrive at a fixed point where every claim is supported.
Honestly you probably want a model that has only been trained on language and literature. Nothing from online discourse.
And even then… writing is personal expression. Here people are talking about commit messages. That’s fine but AI doing writing for anyone and I WILL NOT READ IT unless it’s literally basic tech manual.
We read to hear and engage with people’s thoughts. If someone outsources that to AI then they should be shunned.
So long as there are in fact those things, and so long as it didn't sneak something else in there at the same time, it being just on the knife-edge between sense and word-salad is better than "fix".
Buuuuuut far to often it says it fixed a bug I reported, when it only touched one superficial failure mode rather than the root cause.
Yesterday's issue: Why is zoom/pan randomly failing? It told me it was because it was applying a transformation matrix with every input and sometimes JavaScript gave it a non-invertible matrix (why?) which then propagated NaNs everywhere and you can't update a matrix filled with non-numbers.
Why was it doing that in the first place? Seems to be because it's too motivated to perform quick wins and not sufficiently motivated to do good engineering.
Good thing this was just a game editor. Spiky intelligence: superhuman on some dimensions, total noob on others.
It is, because it includes the key words such as "ownership gate" and perhaps others, which makes it infinitely more informative than just "fix", by pointing at what was in scope, and what wasn't.
I've never had Claude spew that out in a commit message. That being said, I also use my tools properly. Your comment sounds like the type of thing someone who puts "don't make any mistakes" at the end of a prompt and gets upset when it doesn't come out perfect. Like, someone adding "make it better than AAA" is going to do something. At this point, it's really just telling on yourself that this is the output that you get.
Mildly disagree. "Fix" is exasperating but immediately tells me I need to look at the diff. With unconstrained Claude spew, I need to wade through three levels of deep fried LLM-speak before realizing...I need to look at the diff
"Deep fried" is the perfect analogy. LLMs have been trained on themselves so many times that their output is the linguistic equivalent of many rounds of JPEG compression.
I don't get this thread. Just tell the agent to use conventional commit messages and to keep it nice and tight. Are you all just raw dogging agent output with no alignment/conventions?
> Just tell the agent to use conventional commit messages and to keep it nice and tight.
I have this in my claude.md along with guidance on (not) writing comments but it’s still dumps multi-paragraph comments of Claude speak everywhere.
I think a lot of us are talking past eachother, but what I and I think others are complaining about is doing things well, and being minimal. LLMs don’t really do that yet, they can’t look at and simplify a codebase well, even with guidance. They always seem to add rather than subtract. And eventually it becomes an issue. I think they were actually better in this regard with like Opus 4.8, and are now getting even worse (but score better, and are more autonomous).
At home I use Codex, and it’s better as far as language goes at least.
Anyway, it’s like the logic piece necessary to do good work is still missing, and hurt by recent reinforcement fine-tuning. And it leads to massive bloat since more comments = higher scores, but walls of text and the tokens (or cognition if you’re the sad human reading them) aren’t free.
Commit messages as you describe ("fixes", "updates") are inappropriate in any professional context and some coaching should occur to the people doing them.
I have the opposite issue - some of my team members now submit mini-essays generated by the LLM. Like 300-500 word commit messages with everything from the essence of the change up to philosophical design trade off discussions.
Like most writing, what is left out is as important as what is included.
You've gotta be joking. Every AI commit message, summary, and test plan is full of extraneous garbage I didn't need to read (and a lot of it is not understandable)
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.
I can relate to that. Most human commit messages aren't good because the author can't be bothered to write a good one, or doesn't know what a good message is supposed to be, or is bad at writing.
But AI commit messages are still bad. Way too verbose and focused on the wrong level: that of code mechanics. That's just wrong. Messages should focus on the level of intent and design, with the primary purpose being to aid human review. They should include a high level overview of the change, decisions, caveats, information not obvious from reading the diff.
So I wrote a skill that captures these principles and allows the agent to even research past related commits and to ask focused questions in order to uncover the intent rather than guessing and writing a bad one.
Now the AI writes better commit messages than it used to, and even writes better than most humans (who can't be bothered to write a good one). Not better than a good manual message, but you can't have everything.
But sometimes even the good writers are tired or didn't think things through. Being able to compare with the AI's version is still useful.
We have standards we ask devs to follow but I’m not going to make someone go back and change a commit message after the fact. I more care about pull request body copy and I think the rules we have for that have been pretty well adhered too. Don’t even need ai to enforce it.
An LLM can read the diff and do the summary on the fly. What it cannot do, is explain the reason behind a change. That was always that valuable part of the commit msg. The rest can deducted, ofc it's much easier to read a short list or a descriptive title.
Sometimes minimal information is better than extrapolated information, especially when the extrapolation mentally painful to read and has decent probability of being wrong with inaccuracies that waste people's time.
Also:
1. It's often a premature extrapolation from diffs and tickets which you could probably generate later, at need, and likely with even better results.
2. If those commit messages can ever influence future work, then it's just carcinogenic cargo-cult cruft. Pruning outputs (future inputs) is important to prevent weird unwanted drift.
Yeah, I know people who have the same zero-explanation `git commit -mfix` style that they did pre-AI and am baffled. If you can’t be arsed to explain yourself, let the agent do it. It literally takes less work to tell the agent to commit for you and they will always do better than -mfix. I don’t understand it either other than obstreperous “become ungovernable” attitude.
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.
Disagree. I've seen so many PR slop grenades -- they are essentially unreadable. I'd prefer a paragraph or two human written explanations. I suspect people are just taking the default AI text -- which is way too wordy.
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.
Do you measure anything about complexity or brevity? I'm currently working on importing some LLM code and it's 5-10x bigger than it should be for the actual needs.
One of my open questions is how much that increases over time. It could be that is a constant. But it also could be that, say, coding agents will infer false needs from the excess code/docs and elaborate further.
I've only personally utilized it for code _review_ and always ignored the suggested result code instead to understand the source of the issue and try to arrive at a resolution I find satisfactory for my mental model of the issue and solutions I'd prefer.
My take is that the main difference is the approach to problems the coding agents have. They optimize towards presuming a fully working invocation environment, yet checking everything anyway, and then rolling back any changes and re-testing that such changes worked. Which is great for normal types of software but incredibly tedious for anything aimed at less than a fully hands free automated environment.
In other words, AI is very awesome at scope creep of assigned problems and targeting the validation prompts baked into the review system.
I find this shocking though not unbelievable. Could you share how you measure this accurately? I'm interested in integrating such measurements into our services as well.
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.
I find it unbelievable. I've seen the code LLMs write and it sucks compared to what a typical human produces. The only way an LLM is doing better than human programmers is if your human programmers were producing really terrible work.
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.
What exactly do you mean when you say llm generated code? Are people prompting llms for changes and features without reviewing the code or iterating on it and then comparing that to what human writes? Because if so it's not surprising that you're getting worse results. Humans also write code through iteration. You can definitely get llms to write good code by enforcing guardrails and constraints through tooling and agent.md, and iterative reviews to nudge towards what you want. The first pass will look nothing like the committed code. I don't expect the llm to one shot anything.
Believe it or not, most programmers by definition are average. Hence, producing code better than them is not a hard feat to achieve for today's models.
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.
It encodes context it needs into doc comments and regular comments that make them in insufferable to read and so verbose because the comments contain info on other parts of the code base (that might have changed since that comment was written) but were useful to the model for its implementation. I have so far found no way to stop claude from doing this. It will sometimes do it with hand holding but the moment a task takes a slightly large amount of context its back to the word barf.
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.
'ai slop' is hard for me to complain about when it's better than 95% of code prior. The issue is more people trusting it too much to go too far, and you end up with lots of extraneous bullcrap you don't need. Doing too much and too big of a change is still a problem in the agentic world.
1. It’s so much easier using RPis for that work. It can be done with no soldering at all and there are tons of easy to use libraries. Not having to solder is a huge plus IMO and I have a workstation with iron, hot plate, air gun, etc. ready and waiting.
2. Why hate on doing it Python? Even ESP32 embedded development ecosystem treats Python well with CircuitPython and MicroPython.
3. At least they are making something!
4. Even a simple ESP32 is overkill for what you described, so why are you hating on people using an RPi when your suggestion is just as laughable when taking your hardcore embedded stance?
As someone who has been working on embedded work since RadioShack was a good source of components - let’s not gatekeep makers.
1: Not sure what your point here, if you dont want soldering, just use jumper wire, it is not exclusive on rpi.
2: What i mean is the main reason they use Rpi because it can run Python(at least easy, this was before CP/MP mature). If they had spent some effort in C, they can get away with not using rpi.
3: I agree with that, but i really do wish they step out of their comfort zone a little more discovering what is possible.
4: I dont think esp32 is overkill, it's the cheapest and easy to acquire wifi MCU, if you have better suggestion i would like to learn, there is esp8266, but the cost different is not that much.
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!
Interesting how all of the replies so far to your comment assume we’d just release the existing animals into the wild instead of just not breeding more.
As one might guess, the "just" there is doing a lot of work.
Common pets reproduce just fine without our intervention - in practice it requires costly maintenance programs just to keep their population under control (not to mention the massive and ongoing eugenics program required to produce only the desirable breeds/attributes).
If your neighbourhood isn't overrun with stray cats and dogs, that's because someone is funding a spay/neuter program, and someone is funding animal control to round up (and ultimately euthanise) the rest.
All animal husbandry systems have to be maintained via regular culling, and "eliminating" pets would require orders of magnitude more killing
I always assumed the "enslaved animal-free" future would be something that came on gradually, likely motivated by economics (i.e. lab-grown meat becoming cheaper and higher quality than farmed, robotic pets being cheaper and more "trouble-free", etc).
I never felt like anybody seriously thought we'd release domestic animals into the wild to fend for themselves-- that's ludicrous.
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.