Ask HN: Has your whole engineering team gone big into AI coding? How's it going?

They got fired by an AI exploit.

I'm personally using it a lot. For my workplace, the productivity gains are limited by human code review (need a minimum of two approvals) and manual testing. I can produce a ton of PRs, more than ever before, but I was already bottlenecked by review & test in the hand-coding era.

I was thinking last night about whether this is even a realistic moat or not.

Right now, Claude is getting trained by hundreds of thousands of programmers showing it how to ask the right architecture + PM questions.

They're just patterns, like anything else in our industry, and most of them are pretty standard patterns.

Like when I think back on 20 years of software architecture and BA work, I've done the same thing over and over. I must have implemented 4 PO systems, 3 different custom chat systems, SMS systems for reminders, monthly summary emails, etc.

I'd speculate we had a few factors working against us that made us hit the "limit" sooner.

Several different engineering teams from different parts of the company had to come together for this, and the overall architecture was modular, so there was a lot of complexity before we had to start integrating. We have some company-wide standards and conventions, but they don't cover everything. To work on the code, you might need to know module A does something one way and module B does it in a different way because different teams were involved. That was implicit in how human engineers worked on it, and so it wasn't explicitly explained to the coding agents.

The project was in the life sciences space, and the quality of code in the training data has to be worse than something like a B2B SaaS app. A lot of code in the domain is written by scientists, not software engineers, and only needs to work long enough to publish the paper. So any code an LLM writes is going to look like that by default unless an engineer is paying attention.

I don't know that either of those would be insurmountable if the company were willing to burn more tokens, but I'd guess it's an order of magnitude more than we spent already.

There are politics as well. There have been other changes in the company, and it seems like the current leadership wants to free up resources to work on completely different things, so there's no will to throw more tokens at untangling the mess.

I don't disbelieve the success stories, but I think most of them are either at the level of following already successful patterns instead of doing much novel, or from companies with much bigger budgets for inference. If Anthropic burns a bunch of money to make a C compiler, they can make it back from increased investor hype, but most companies are not in that position.

They were all sacked.