News for hackers. Stuff that matters.
Re:Software is breaking down at a systemic level by dotdi on Monday November 16, 2026 @01:51PM (#50521329)
It does have to be this way, unfortunately, because AI bros will press to have as much software produced at the absolute minimal cost possible.

I've seen it first hand. 70 people fired, 20 people left. The 20 that are left take on all the work that was done before, plus some extra, because every company now has a new AI product, obviously. AI agents make us so productive. Every review is a 30 second LGTM on 500 new lines of code. Confluence filling up with AI slop.

A few weeks back I saw, first hand, a DevOps lead getting ready to ship a big update to performance-critical product where Opus 5.5 suggested they completely turn off JIT everywhere because they were running into a HotSpot C2 optimizer bug that would make the first request after a restart fail with a 500. Actual fix was a one-line adjustment somewhere in a library.

People are scared of being replaced, so they need to appear as productive as possible.

Re:Software is breaking down at a systemic level by cmiles74 on Monday November 16, 2026 @01:53PM (#50521365)
I suspect the majority of reviews had been a rubber stamped LGTM. Often the minority with substantive feedback were heeded and changes made; I'm not sure that is happening anymore.
Re:Software is breaking down at a systemic level by CharlieDigital on Monday November 16, 2026 @02:06PM (#50521540)
You can be productive and guide AI to operate in a more compliant way: by writing down basically everything you know, every heuristic you have, documenting the correct patterns, documenting the framework level approach, explicitly spelling out what's good code, writing down detailed specs for an agent to work on, writing the test plan, etc.

A lot of devs still think their job is to produce code; it's actually to produce all of the guidance and structural scaffolding for the agents ("the harness") to guide its behavior and output.

A concrete example: I wrote a small library[0] (MIT, OSS) that improves how agents write unit and integration tests. This isn't product code, but this makes the agent better at writing the tests it uses to verify its work. (Tests become denser, more semantic, less context, type-checked setup, etc.). You can't expect an agent to do this by itself; the human needs to produce the scaffolding.

[0] https://github.com/zeeq-ai/zeeq-biome

Re:Software is breaking down at a systemic level by boorang on Monday November 16, 2026 @03:40PM (#50522938)
agree- this is how i name variables, this is how we handle third party APIs, this is how we handle caching and here are some heuristics for when we want to cache and when we want to avoid it, etc. etc. all coded up in a nice documentation tree with links in the agents.md that say "when integrating with third party APIs, read docs/integrating-with-third-party-apis.md".

i have written alot of this type of documentation as an architect for human teams, and i find it works for agents as well.

Re:Software is breaking down at a systemic level by skydhash on Monday November 16, 2026 @04:18PM (#50523433)
> A lot of devs still think their job is to produce code; it's actually to produce all of the guidance and structural scaffolding for the agents ("the harness") to guide its behavior and output.

This basic reasoning is wrong and leads to “orchestration porn”. Thinking that you can laid down rules to automate software production like it’s a factory pumping out product.

What you forget is that software are grown iteratively, not guided down some assembly line. Every patch is a revision of what the software should do, not the next step od a workflow.

So stuff like patterns, architecture, tests,… are helpers for communicating the purpose of the software. They’re not really relevant to the software itself as the computer would be happy with just a single file.

You have a software that’s needed to fulfill some needs, you have a team of people where each brings expertise to build it. Workflows are built so that everyone how to contribute, what they can depends on, and what others need. When there’s a failure, we add the missing information. When there’s need to do some changes, we inform everyone impacted.

Everything is information and communication related. Information about the system and communication between everyone that interacts with the latter.

So devs do not think their job is to produce code. It is to take requirements written in ambiguous natural language, sometimes incomplete and contradictory, and to design a solution that is formally written while taking care that all statements are coherent.

Making things coherent (aka correct) is what takes the majority of our time. The other is gathering requirements. The actual typing of code is pretty much instinctive, just like you don’t check the orthography of words like “concrete” or “guide”, and rely on the spellchecker for more difficult one.

The “orchestration porn” part is that there’s no mention anywhere on how you think correctness and be improved or even maintained as part of your tool.

Re:Software is breaking down at a systemic level by Fr0styMatt88 on Monday November 16, 2026 @05:33PM (#50524413)
I view the thing I’m ultimately providing to an AI agent is ‘executive function’, in the sense of how it’s used when talking about ADHD; one of the core executive functions is retrieving the right skills and/or information to use, at the point of performance.

AI agents don’t have this in a sense; or they do, but it’s average and stochastic. We have to be in the loop to provide judgement and manage the agent’s context; the content of that context steers the agent in the direction that our judgement tells us the development should go, to meet the various requirements. Some of those requirements are around the software’s function, some around maintainability, some around understandability, etc.

I think scaffolding is good at decreasing the amount of repeated mistakes and ensuring the agent can request and receive information efficiently. I think software factories are too self-referential; I’m not set on that opinion though and like I’ve said in another comment, I will fall down this rabbit hole at some point just to see what it’s like.

So many times I’ve wondered “you know how to do this, so why didn’t you just do it the first time?” — the old “Oh you’re absolutely right! That’s a much better way to do it!”.

It’s not that the model doesn’t have the knowledge, it’s that it doesn’t access it at the time it is needed. Part of my job now is to collaborate with the models and the tools.

Re:Software is breaking down at a systemic level by skydhash on Monday November 16, 2026 @07:08PM (#50525482)
From my experience there's always two parts in working with code. The deterministic part where you can derive information from the code itself and do some action, mostly used by static analysis tools (type checker, linting,...) and there's another much harder to define part like "this part of the code is unreadable and/or does not mean what the requirement says".

The first is solved by deterministic tool as code is already formal, so the grammar is very strict and fully defined. But the second part is entirely human dependent of what the end result should look like, even when the same semantics is being kept. That's why two people asked to implement the same task will code it differently even if from the point view of the machine, they're equivalent.

Maintainability and readability is not about software correctness. It's about how the human mind can absorb what the software should do, aka the specs embedded in the code, which is just formal notation. If it's easy, then the software correctness is easy to check and validate. And when the requirements changes, it's easy to apply the needed modifications.

So asking agents to improve upon that is like asking an agent to write an email. It's an alienation of human-human communication.

Re:Software is breaking down at a systemic level by chickensong on Monday November 16, 2026 @05:38PM (#50524472)
Your argument seems to be about refuting a generalized one-size-fits-all approach, which can have its place, but there's nothing preventing per-project "orchestration porn" that works very well. Bind the harness to the project and your agent will help you with the non-code tasks as well.

> there’s no mention anywhere on how you think correctness and be improved or even maintained as part of your tool.

The first paragraph is literally a list of examples, followed up by a specific library that helped the OP. The paragraph you quoted explains where the maintenance lies.

Re:Software is breaking down at a systemic level by xmcqdpt2 on Monday November 16, 2026 @05:11PM (#50524129)
Do you have eval testing? Benchmarks? Deterministic model checkpoints? Deterministic harness versioning?

Building "orchestration" without being able to deterministically measure improvements is not engineering, it's cargo cult.

Re:Software is breaking down at a systemic level by Terr_ on Monday November 16, 2026 @06:04PM (#50524823)
[delayed]
Re:Software is breaking down at a systemic level by asdfman123 on Monday November 16, 2026 @02:11PM (#50521608)
> AI bros

You have to stop thinking this way. It's our job to do what our management wants us to do, which is often to produce as much software at the lowest cost possible.

There are legitimate criticisms about AI use and how AI has changed the profession, but you have to learn which battles are worth fighting.

Re:Software is breaking down at a systemic level by dotdi on Monday November 16, 2026 @02:35PM (#50521957)
Just like crypto bros a few years back, where we "do what our management wants us to do", built stupid-ass blockchain into every every which app that didn't need it, and when it doesn't sell get blamed for it.

Personally, I was asking "but what's the use case" in every meeting. "Why would somebody pay for this". "Who's the customer". Right now the vibes are quite similar to back then.

Re:Software is breaking down at a systemic level by rsoto2 on Monday November 16, 2026 @02:59PM (#50522314)
Doing what management wants you to do blindly is an easy path to ruining the company and losing your job. We used to joke that the true mark of a senior engineer is being able to tell management when their ideas are stupid, will not work, and "no."
Re:Software is breaking down at a systemic level by GolfPopper on Monday November 16, 2026 @03:38PM (#50522907)
We were just following orders!

The refusal to take responsibility for the consequences of one's work is one part of a vast complex of machines that normalize the horrific. We have met the shoggoths and they are us.

Re:Software is breaking down at a systemic level by Toynbeeidea on Monday November 16, 2026 @03:38PM (#50522914)
Management are AI bros. Bro.
Re:Software is breaking down at a systemic level by palata on Monday November 16, 2026 @04:43PM (#50523725)
> It's our job to do what our management wants us to do, which is often to produce as much software at the lowest cost possible.

Have you ever been in a situation where you did what the management wanted you to do for years, regularly warning them that you could not write good code while doing what they wanted but being dismissed because they knew better? And have you ever been in a situation where you finally got your "I told you so" moment after years, when they actually realise it won't work?

I have. You know what happens then? It's not their fault. Best case, they explain why you couldn't have known better because it was hard. Worst case, they fire you because... well you built that mess, remember?

Re:Software is breaking down at a systemic level by rsoto2 on Monday November 16, 2026 @02:56PM (#50522260)
Dude, you just didn't write down the rules and the patterns effectively. Just write down "don't completely turn off JIT" /s

Damn if only there was a way to write strict rules and patterns in the english language that could be converted into strict instructions for the computers and ways to verify those instructions...