I was starting from scratch and mainly relying on Opus/Sonnet 4.

I also kept running into the Godot 3 vs 4 issue before adding specific guidance about this into CLAUDE.md

LLMs are really good at C# (and tscn files for some reason), so that solves the "LLMs suck at GDScript" problem. Also, C# can be cheaper in terms of token usage (even accounting for not having to load the additional APIs): one agent writes the interfaces, another one fills in the details.

Saying this because I had really enjoyed vibecoding a Godot game in C# - and it was REALLY painful to vibecode with GDScript.

Can you actually introduce that into the decision making? That is, you would:

1. Have the LLM come up with N many potential actions

2. Run XMage run in parallel and provide the outcome for each different action

3. Revert XMage to the original state

4. Provide the LLM with the different outcomes and have them choose the action/outcome pair rather than just the action

This would actually help them analyze the counterfactual outcomes more effectively and should prevent 99% of the blunders

If you happen to be token rich, you could even do this in a MCTS manner and have them think really deep

My take was that it’s easier to trace who is doing what (and what the agent hierarchy looks like) when agents’ locations are fixed.

Comments URL: https://news.ycombinator.com/item?id=46289310

Points: 1

# Comments: 0

Agreed, but how else are you going to scale mostly AI written code? Relying mostly on AI agents gives you that organizational complexity.

> Given how long gpt codex 5 has been out, there’s no way you’ve followed these practices for a reasonable enough time to consider them definitive

Yeah, fair. Codex has been out for less than 2 weeks at this point. I was relying on gpt-5 in August and opus before that.

This was my journey: I vibe-coded an Electron app and ended up with a terrible monolithic architecture, and mostly badly written code. Then, I took the app's architecture docs and spent a lot of my time shouting "MAKE THIS ARCHITECTURE MORE ORTHOGONAL, SOLID, KISS, DRY" to gpt-5-pro, and ended up with a 1500+ liner monster doc.

I'm now turning this into a Tauri app and following the new architecture to a T. I would say that it is has a pretty clean structure with multiple microservices.

Now, new features are gated based on the architecture doc, so I'm always maintaining a single source of truth that serves as the main context for any new discussions/features. Also, each microservice has its own README file(s) which are updated with each code change.

- Better structured codebases - we need hierarchical codebases with minimal depth, maximal orthogonality and reasonable width. Think microservices.

- Better documentation - most code documentations are not built to handle updates. We need a proper graph structure with few sources of truth that get propagated downstream. Again, some optimal sort of hierarchy is crucial here.

At this point, I really don't think that we necessarily need better agents.

Setup your codebase optimally, spin up 5-10 instances of gpt-5-codex-high for each issue/feature/refactor (pick the best according to some criteria) and your life will go smoothly

+100 on the footnote:

> agents or workflows?

Workflows. Workflows, all the way.

The agents can start using these workflows once they are actually ready to execute stuff with high precision. And, by then we would have figured out how to create effective, accurate and easily diagnozable workflows, so people will stop complaining about "I want to know what's going on inside the black box".

"The model often attempts to use a hallucinated bash tool rather than python despite constant, multi-shot prompting and feedback that this format is incorrect. This resulted in long conversations that likely hurt its performance."