[tharkun__]

    “people like me are still needed” is just a desperate form of self-persuasion.

No, no it's not. I've seen what "PM armed with an LLM" will do. Trust me, if you're a decent enough Full Stack software engineer that can take an idea and run with it to implement it, you'll have a leg up over the PM with the idea that has no idea how to "do computers".

Most of what these PMs can produce nowadays turns boardroom heads, sure. But it's just that: visuals and just enough prototype functionality that it fools the people you're demoing to. Seen enough of these in the recent past.

Will there be some PMs that can become "software developers" while armed with an LLM? Sure!

But that's not the majority. On the other hand, yes there are going to be "software developers" that will be out of a job because of LLMs, because the devs that were FS and could take an idea from 0-1 with very little overhead even in the past can now do so much faster and further without handing off to the intermediates and juniors. They mentor their LLM intern rather than their intermediates and juniors. The perpetual intermediate devs with 20 years of experience are the ones that are gonna have a larger and larger problem I'd say.

The Staff engineer that was able to run circles around others all along? They'll teach their LLM intern into an intermediate rather than having to "10 times" a bunch of perpetual intermediates with 20 years of experience.

[rufasterisco]

I agree with you overall, yet there’s one flow that works for me. Instead of speccing out a feature, I let PMs vibe code it. I then have the exact reference I need to build.

Maybe LLMs oneshotted the right way, maybe it needs fixes, maybe some fundamentals are misunderstood, in any case it’s easier for me to know what I need to build, for the PM to be aware of some limitations (LLMs do the job of pushing back and explaining) and overall for us to have to the point conversations.

It is somewhat orthogonal to what you say, when you focused on dev seniority, so that part stands true.

But I think “PMs armed with an LLM” can, when properly used, add a lot of value to the dev process.

[nunez]

> I agree with you overall, yet there’s one flow that works for me. Instead of speccing out a feature, I let PMs vibe code it. I then have the exact reference I need to build.

Like BDD, but with something more accessible than Cucumber. I'm totally here for that.

It would be nice if people also committed their initial prompt and chat session with the LLM into their codebase. From a corporate standpoint, having that would be excellent business logic as code, if the code is coming from a PM or a stakeholder on the business side of the house. From an engineering standpoint, it would be an excellent addendum to the codebase's documentation.

[tharkun__]

FWIW, BDD and frameworks like Cucumber don't work at all in my experience. The people that'd need to fill these out don't do it properly (they can't) and then we, devs, are stuck with brittle and un-debuggable stuff that's worse than if we just used regular code to encode what we understood from them.

It's the same reason (most) PMs armed with an LLM still won't get anything usable done. They can't do it properly. They still need devs. But the gaps are shrinking. Some few PMs can get stuff done w/ both Cucumber, could wireframe UX with previous tools and can now do so much easier and better with an LLM.

    It would be nice if people also committed their initial prompt and chat session with the LLM into their codebase

I doubt you'd want this. It's a chat session for a reason. It's gonna be huge wall of text, especially if you meant to actually include all the internal prompting the LLM did while it was working. You'd also have all my "no dude, stop bullshitting me! I told to ignore X and use Y and to always double check Z and provide proof".

It would only "work" if every single piece of feature you wrote was 100% written by the LLM from a single, largish and well defined prompt, the LLM works for a few hours and out comes the feature. And even then you have no reproducability (even if you turned around and gave it to the exact same model, no retraining, newer model, system prompt etc.).

[rufasterisco]

There are ways to play around the single wall of test issue. Mostly, git lfs.

When it comes to “no dude stop etc etc” … that is valuable information. You can extract that and put down rules for agents so that you stop repeating it each time.

Same can be done at PR, so that you can review not just the code but also how you got there.

It’s trivial to go from session to a nicely polished html with side by side conversation.

If you want to try, username at gmail, I have a private repo with it running. I value critics, sorry for the plug ;)

Oh, on the different models side, i don’t see the advantage of reproducibility, or better, I don’t think I understand what you mean, can you help me see it?

[tharkun__]

I don't understand how "wall of text" is related to git large file support. The wall of text is a problem for me, the human. Sure, there are ways, like "be brief", caveman etc. In a large repo with lots of different people over time, I can't see how it won't just be wall of text again. It's just too much. TL;DR. And coz DR, the LLM will have buried bullshit in that text, which future session might read and "believe".

As for "no dude", no that can't be put down into rules. Not all of it anyway. We have stuff encoded in the repo wide md file, I have my personal one etc. and the various agents still don't do what we tell them to in all cases or a new model comes out and it no longer works. For example, for finding the root cause of a bug, it's very important to have actual proof and references. It's getting there w/ my instructions in the .md but it doesn't always work and I do have to "dude" it from time to time.

Is that back and forth valuable to have in files that are going to be part of the repo? I very highly doubt it. Having new rules that came out of the back and forth in a checked in AGENTS.md, sure, that is valuable. Or nowadays in individual "skills", like a "root cause finder" skill that can have very specific instructions about being thorough in proving its "found the smoking gun" BS ;)

I've seen enough PR descriptions created by the agent. Fluffy wall of text that looks good but is factually wrong. Seen it way too many times. Too many people just look at whether it looks good and then pass it off as truth. I'm tired of it and making that into "nice HTML" doesn't make it better. It just makes it look even nicer but not more true.

Re: reproducibility. My parent poster (and I guess you as well) wanted to have the prompt/conversation as "documentation". I don't see why that would be helpful. The only reason I could see would be for "reproducibility", which you won't get with an LLM. I don't see why else, but do tell me.

What I can agree could be valuable are the "why"s. I.e. the stuff that already should have been part of the ticket/requirements document. If you want to store that inside the repo as text files, instead of the original tickets or documents, that's fine of course. But I don't see how a "recording of how the code came to be" is valuable. It's like having a recording of all my IDE keystrokes and intermediate code state in pre-LLM days. Not valuable. What's valuable are the requirements and the outcome (i.e. code). Not "the thing in between".

Now don't get me wrong. Recordings of how people code/use their IDE can be a valuable teaching tool. Both as good and bad examples. And the same can be true for an agent coding session.

[rufasterisco]

let to unwrap, let me try to do it

i misunderstood "wall of text" (i was thinking about bloating repo with it), my solution to understanding is just to create ad-hoc tools to parse the json

i coded a web ui with simple toggles: show me what user said, what llm said (nice to see what I was thinking about, nice to see how LLM came up with solution X, you get tools calls, maybe it found something i didn't think about or viceversa) you can search/grep (.ie: did i consider idempotency when i build feature X? open session, search/grep idempotency) you can, up to some point, resume the conversation (yes i know, cache busting makes some usages of this impractical, but in general resuming and asking "when we did this, did we think about that" tends to work... let's say that research is ok, time travel, meh)

overall, one of the advantages of LLMs is to be able to direct then ad data for insights, via standard CLI tools, via specific prompts, or building some mini tools (yeah vibe coding is fine sometimes) whatever my question, if i have data i can have an answer

LFS helps with the second aspect (buried bullshit). Unless you smudge, you have a pointer, and that is just 3 lines. You need to learn some ergonomics, but ok, some of us learnt how to use Jira XD

Taking your position a bit further, yes, committing chat sessions implies that you also need to review them so that bullshit doesn't filter through. Milage varies based on your personal preferences, which project you are working on, and many more heuristics. Some will find it boring, some will think it's good project maintenance, all should be able to find a way to handle this based on their preference.

It is also nice to pointout that cleaning bullshit doesn't need to happen at merge. LFS blobs being stored separately, you can have side flows helping you out, without clogging yoou CI pipelines.

"no dude"-> rules you can put down SOME rules usually this happens to me at PR. I am tired fo saying "you should always check X", so i bolt it down "someplace". I am running the usual motions i suppose most of us try to adopt: put this down in agents.md, in folder x or y, in path-scoped rules using agents, in memory files (i am exporting/importing those too), in subagents that review code before PRs.

in the end it's an unsolved problem at large, but 1. hopefully it will get better, my feeling is that it's just a cambrian explosion, and the fittest will survive... (also, owning the harness should help, i suppose .. i use claude code :D ) 2. in a team, having personal styles surface is valuable. "dude don't do that" is quite often .... design. When rules go in the repo, at least we can find an agreement in person, and at PR is not about linking a document you read at onboarding, but finding out why the agent did not respect the rule. To me, that is more grounded in a tool. 3. rules are ... not static? We change our minds? We get better at things? We want to experiment? I am not advocating for a perfect rule system that replaces me, but for a good enough one that removes cruft from my daily job.

I think my approach is actually helpful when it's time to find root causes (YMMV). Via tools that parse sessions, you can see when that specific portion of code has been written with a better granularity. During that bit of the conversation the user was worried about X and asked AI to do Z and AI read this and that file and "thought" this and that and wrote that piece of code. Maybe the user was making wrong assumptions, maybe the LLM did not read the correct files or instructions, in any case you have a better tool for investigation. It's up you to decide wether to use it, wether this lead to just solving the bug or also fixing instructions, etc, i am just saying that it actually helps to have some measure of the context on which this change made sense.

"Fluffy wall of text that looks good but is factually wrong. "

it might be good or bad, right or wrong, but what is in the sessions is the truth of what happened. PR desc are horrible, i share that feeling with you, but having the story of how that thing happened is just not the same as "final summary of what we did in the past X hours".

As a sideline: LFS doesn't really pollute your repo once you get to learn its ergonomics. Having chats in LFS also lets you approach this

Reproducibility... To me those conversation are basically the history for decisions taken while implementing. They are documentation. The real problem with docs was that no-one has ever liked writing them, nor it was easy to implement a standardization around them. If you just record/log, there';s no extra effort needed, and once there tools and LLMS are pretty good at helping us extract insights.

I am also assuming, there is a correlation between quality in the conversation and in the code. I know, i'm being hand-wavey, but overall i think critical thinking is what makes code better, and being able to see if/which it has been applied can be a good proxy. I ask for forgivness already: I not going down the rabbit hole of quantifying quality etc. It's a broad statement that should be taken with a grain of salt.

If you want to go abstract, you can think of coding as going from thoughts to 0-1 in bits. We have high(er) level languages that help us organize thoughts to help us so that we can better keep them in our cognitive flow/load. LLMs are an upper layer, that scrambles the code and make it more difficult to grasp. But the reasoning behind the code is now available, and quite easy to parse. I think this is the core point to me. Code is an intermediate artifact between thinking and bits. Now we have a second artifact: the conversation/decision that led to that code. Why are we not storing it?

disclaimer: I am, of course, mildly in love with my own project and ideas, so possibly i like this too much just because i built it. IKEA effect or whatever.

[rufasterisco]

I am actually working on that. Want to beta test? :)

Can invite you to the, for now private github repo.

Any feedback would be helpful!

[rogual]

What I'd love to see is videos of nontechnical folks using language models to create software.

When I use them myself, I just see them crushing it and think, this thing is now doing my job for basically $0, I am no longer economically relevant. But I've spent a lifetime learning to program, so it's possible I only get good results because of the way I think to prompt it.

I really can't get the outside view so I can't decide whether AI is going to make me homeless or not. I think we need the videos.

[_aavaa_]

If you need comfort just read the story of the week where a “technical” founder gave the LLM full access to their production environment and it wipes everything.

[ricardobayes]

Oddly, devops seems to be the "last bastion" of our trade, as they seem to be only ones pushing back against PM vibe-coded stuff. Usually while those projects look aesthetically pleasing, they start to fall apart when met with devops requirements for environment values, cybersecurity, etc

[dasil003]

I agree with you, so far what I see is that AI amplifies an individuals output in many domains, but the value of that is 100% contingent on their judgment. It changes the economics of many tasks, but fundamentally it can't really help you if you don't actually know what you want—which is sort of a shocking number of people in the corporate world where most people are there for a paycheck, and perhaps to pursue some social marker of "success".

I'm under no illusions about the goals of AI company execs to justify their valuations (and expenses!) by capturing a huge chunk of global employment value, and the CEOs of many big companies whose financials are getting squeezed for all sorts of reasons and are all too happy to jump on the efficiency narrative of AI to justify layoffs that would have been necessary anyway. Also, AI will keep getting better and it could certainly will move up the food chain—it's already replaced a lot of what I did and I assume capabilities will continue improving for a while even after model capabilities plateau as we improve harnessing, tooling and practice.

So yeah, it can replace a lot of what we do, but I'm not running scared because every step of the way I've seen software people are the ones who actually get the most out of LLMs. Sure it can write all the code so the job changes, but even our workflows completely change, it's giving us more of an edge (if we're open to it) than it does to anyone non-technical. At this stage it still feels empowering on an individual level.

Now I do worry about the consolidation of power and wealth in a tech oligarchy, but that's an issue we need to deal with at a societal and government policy level. Essentially, I can see AI as having radically different outcome potential based on how it's governed. In one way it can be very empowering to small teams, and reduce coordination costs, and increase competition by allowing smaller groups of people to make more scalable companies. But it could also lead to unprecedented concentration of wealth and power if a small set of AI companies are allowed to capture all the economic gains. I don't think there are any easy answers, but I do feel hopeful that we can figure something out as a society—it certainly seems to be creating some unified sentiment across political lines that have been so polarized and divisive over the last decade.

[cushycush]

It amplifies by 1000x is the problem for our jobs. However, I do agree that developers with experience are needed to actually harness these tools. I’ve been able to do wonders with them, but I can’t see a junior dev doing 10% of the work that I can with them.

[TheOtherHobbes]

It's a strategy problem, and the current version of the US is spectacularly bad at strategy.

Once upon a time the US had visionaries steering DARPA and making useful bets on the future.

Now strategy is defined by stonks-go-up, quarterly returns, democracy bad, and CEO narcissism, and that's a potently catastrophic combination.

[bambax]

I think this is exactly correct.