vividfrier

As part of a reorg, my team received a new system to maintain. I sat down with a great engineer and together we refactored that shit to get into something more maintainable. I became the go to guy for that system because our redactor led to such a deep understanding of the codebase.

Now in the age of AI... we adopted another system from a team and when we asked for knowledge sharing to prep for the handover the answer we got was "do we still do that? Just ask Claude".

It's now been a few months. We've shipped features in this new system. I still have no idea how it works. Okay I kind of know, but only at a very shallow level.

AI is the worst thing to happen to our industry.

Good points and questions and I don't have the answers.

I've definitely thought about how I currently offer something to the company because I know these systems and can stop the agents from doing weird shit. But in a greenfield project I would probably (definitely) not get the same understanding.

I think as we figure out best practices - you'll start to see that you can rely less on humans. More tests, more acceptance tests of critical business logic, etc.

I think we might get to the point where I'm not really adding value anymore because I dont know the codebase well enough to stop the agent. But then again - the cost of code is getting cheaper and when you reach that state where agents can't reliably work in the codebase due to AI slop - maybe you just start over? Kick off a few agents over the weekend and come back on Monday to a new (hopefully leaner) codebase? Run it in shadow mode next to the production service - ask the agents to fix any discrepancies and iterate until you have a simpler service?

I dont know what will happen. But I dont think we'll go back

Github's issues aren't really a vibe coding issue though - right? It's more of a scalability issue due to vibe coding? Didn't the CTO go here on hacker news and say that they had 1bn commits in 2025 and are on course for 14bn commits in 2026?

Wait, just need to get all of my em dashes out!

Seriously, not a bot. Just a software engineer who feels gaslighted because I see AI used in one way at work and then I go to Hacker News and I feel like I am using a different technology compared to everyone else.

And don't get me wrong. I would like to be more skeptic about AI because I enjoy writing code, I enjoy a high salary with great benefits. But with the speed and direction we're seeing now (so I am not only looking at this specific point in time but rather also the direction and the fact that no one knows what they're doing) - I do worry about losing this. So I am definitely crossing my fingers that it is a bubble but I just don't see the evidence yet.

I don't understand the hostility here at Hacker News. The common theme across all of these discussions is of course that AI is bad and will cause the industry to crash.

Just like I need to keep in mind that not everyone work in a big tech(ish) company where tech stacks are standardised and many problems are solved centrally, I feel like people also need to keep in mind that not everyone has a horrible experience with AI.

And I also want to clarify that I hate AI. I loved writing code, I loved having a comfortable job with a good salary and good benefits. While the company I work for haven't done "AI layoffs" yet I feel like it's a matter of time because I'm not only looking at the state we are right now but also what the direction and speed is. It was only back in October I felt like AI was a bubble about to burst cause I wasn't getting enough value out of Claude Code. And then ofc Opus 4.5 happened and it changed my view completely. And we're a few months into using 4.5/4.6/4.7 (and I'm not an Anthropic shill, currently I am using Codex most of the time) but I was hoping this career would last me decades. But where will be 5 years from now? 15 years from now?

I just want to provide my perspective from a big tech company where I feel AI is doing more and more parts of my job. It's not perfect and it gets things wrong but I mean... humans do as well?

I feel like I'm in a different field compared to the rest of hacker news.

I'm in a big tech company where everything is standardised. All our microservices have the same tech stack. We're in a monorepo. Most microservices are... I wouldn't say tiny or micro but small enough.

And I haven't written a single line of code myself since what - February maybe?

We still haven't seen an increase in incidents, we ship more features at a higher quality. We address the tech debt we didn't have time for in the past.

We still require a code review for any change and it's becoming a bottleneck - for sure.

But it all feels... Mature and the next step of software engineering.

We don't really vibe though. At least I don't. I see it more as comment driven development. I need to understand the code and what I want to achieve where in the codebase but I'll leave godo comments explaining this before asking an agent to fill in the blanks.

I feel like git started to feel outdated overnight as the company I work for went agentic development first.

I fought for years trying to convince my colleagues to write good commit messages. Now Claude is writing great commit messages but since I'm no longer looking at code - I never see them. I don't think Claude uses them either.

Branches are now irrelevant since all agents work in worktrees by default. But worktrees are awkward since you run out of disk space fast (since we're in a monorepo).

There is a constant discussion ongoing whether we commit our plans or not. Some argue that the whole conversation leading up to the PR should be included (stupid imo).

The game changed completely. It isn't weird that people are wondering if the tools should as well.

Definitely feels like there's opportunity to build something better

> A protocol must offer direct benefits to users, so that they keep participating in the network

As someone who tried to give all of the decentralized social networks a shot... something I realised along the way is that they are never going to fly because they are not giving you dopamine kicks like the big tech giants are. I ended up forgetting to visit Lemmy or Pixelfed or <whatever> because I had 2-3 times when I opened up the app and saw the exact same content, giving me a feeling of "nothing is happening here" and thus, I didn't need to check in.

I mean, even Signal has that Instagram story function but I have never seen a contact use it because no one goes to Signal "just to scroll" or whatever. They go there to send or read a message.

Any social media needs content for people to visit. They need to make people feel like they are missing out if they are not visiting. Otherwise, they're just going to end up as an app on the phone which is never opened.

> I find anything else, I spend more time coaxing them into doing 85% of what I need that I'm better off doing it myself.

You must be working in a very niche field with very niche functionality if that's the case? I work at a company just outside of FAANG and I work in compliance. Not a terribly complex domain but very complicated scale and data integrity requirements.

I haven't written a single line of code manually in 2 weeks. Opus 4.6 just... works. Even if I don't give it all the context it just seems to figure things out. Occasionally it'll make an architectural error because it doesn't quite understand how the microservices interact. But these are non-trivial errors (i.e. humans could have made them as well) and when we identify such an error, we update the team-shared CLAUDE.md to make sure future agents don't repeat the error.

Same. Whenever an article like this one pops up the comments seem to be filled with confirmation bias. People who don't see a productivity boost agree with the article.

I work at tech company just outside of big tech and I feel fairly confident that we won't have a need for the amount of developers we currently have within 3-4 years.

The bottleneck right now is reviewing and I think it's just a matter of time before our leadership removes the requirement for human code reviews (I am already seeing signs of this ("Maybe for code behind feature flags we don't need code reviews?").

Whenever there's an incident, there is a pagerduty trigger to an agent looking at the metrics, logs, software component graphs, and gives you an hypothesis on what the incident is due to. When I push a branch with test failures, I get one-click buttons in my PR to append commits fixing those tests failures (i.e. an agent analyses the code, the jira ticket, the tests, etc. and suggests a fix for the tests failing). We have a Slack agent we can ping in trivial feature requests (or bugs) in our support channels.

The agents are being integrated at every step. And it's not like the agents will stop improving. The difference between GPT3.5 and Opus 4.6 is so massive. So what will the models look like in 5 years from now?

We're cooked and the easiest way to tell someone works at a company who hasn't come very far in their AI journey is that they're not worried.