Return to Manual Coding - Harness engineering: Leveraging Codex in an agent-first world

Questions about what happens when teams want to stop using AI tools, implications of bloated codebases for future maintenance

The rapid inflation of codebases through AI-driven generation raises urgent questions about whether teams can ever realistically return to manual coding once a project reaches a massive, machine-oriented scale. While some developers are already seeking to reclaim the "driver's seat" by shifting from total generation back to minimal autocomplete to preserve their flow state, others envision a future where traditional repositories are replaced entirely by lists of prompts. Ultimately, there is a growing concern that code is evolving into a form of "modern bytecode" designed for machines rather than humans, creating a bloat that may eventually leave even senior engineers unable to maintain the systems they’ve helped create.

View on HN · Topics

Here's a fun one: firefox lists its current count at about 2.5M LOC, from roughly 1M commits during the years.

You end up with about 3 lines added per commit, which is not ridiculous when you consider that most would be editions rather than full additions.

Here, we have 1500 PRs and 1M LOC, which is about 650 added LOC per PR. Remember, not 650 lines total in the PR, but +650 balance after additions-removals.

Fun questions for attentive readers:

- What does a project growing at a rate of one full firefox-codebase worth of LOC per year look like, a decade down the line?

- What does the line count say about the verbosity of the tool, and what does it say about outcomes that the purpose of the project isn't clearly disclosed?

- Do we have reasons to care about LOC in a world where we don't write code manually? What happens to token usage numbers when the codebase is significantly larger?

- If it was confirmed that LLM usage blows up your line count, what's the implication for codebases that want to return to manual coding after months of usage? (Say, because the tool gets expensive).

View on HN · Topics

I’ve been vibe coding a lot over the past year or so, and I think I’m going to stop. In fact, I sort of want to challenge myself to see, can I go back to a sort of the fork in the road with the old copilot autocomplete workflow and really maximize that. Be in the drivers seat for most of the code being written, but find ways to use AI to really enhance the flow state / remove blockers. Tools only minimal actual code generation.

View on HN · Topics

I like the idea of saving the work done into files - helps to prevent the llm from redoing the same work. Maybe one day instead of code in a repo it will just be a list of prompts.

View on HN · Topics

That's true now. But in the world of this article, it's also the senior engineers that get nailed. In the world of this article, all code is like what machine code or bytecode is now - it's designed to be used by the machine, not the human, because the expectation is that humans will rarely, if ever, touch it.