Will AI keep us stuck in 2020 architectures?

Will AI keep us stuck in 2020 architectures?(sagenschneider.blogspot.com)

3 points by sagenschneider 85 days ago | 6 comments

I don't think so, at least not if you're using agents smartly for software engineering and not just firing prompts off. There's the default way agents build stuff, but they're very steerable and it's easy, with hard rules (like linting) and soft rules (like skills and AGENTS.md), to guide them to actually make half decent software architectures however you like.

sagenschneider 85 days ago | |

Agreed. AGENTS.md and skills are the documentation level from the linked post that hands AI the context its training lacks.

However, this only works if you know a better architecture exists. Most won't and they'll use the "defaults". And these defaults is what the next model trains on. Individually you can steer, but I'm concerned it won't be enough to steer the critical mass of the training data.

re-thc 85 days ago |

No.

Just create your own guardrails. Lint rules. Hooks. Whatever. AI also keeps training on newer data. We move on.

sagenschneider 85 days ago | |

And how many projects are actually doing this?

And if they are, how many are keeping this up to date?

re-thc 85 days ago | | |

> And how many projects are actually doing this?

How many are following any best practices? Whose problem is that? Not AI.

> And if they are, how many are keeping this up to date?

And how many projects use the latest Spring (mentioned in the article)?

Don't blame AI. Blame the humans.