Hacker News Reader

Comment by zahlman | Hacker News Reader

> It is a wizard-style AI tool that will guide you from idea → vision → tech spec → implementation plan.

(And then the implementation plan is fed to the same sort of AI that you were going to give the "idea" to in the first place.)

If doing this gives good results, then it shouldn't be necessary.

View on HN

This the standard current approach for most models/agent tools because models can do well at "make a plan for this" and "execute this step" but are less good at generating a response string that includes both the plan and every step of the execution without intermediate prompting/redirection/focusing. Helps fight context drift and maximize effectiveness/efficiency of the predictions.

Most advances in tools I've used in the last two years are exactly this sort of "automate the steering and feedback loop that the prompt goes through" automated-fairly-boilerplate-sequencing of refinement of initial idea -> plan -> execution -> feedback.

Thanks for saying this.

Why? From first principles you can deduce why it makes sense this could work, they are auto regressive next token prediction engines. As to efficacy, well that you would need to try it and see, but I see no reason to dismiss the idea out of hand.

I mean, it would be great if it wasn't necessary - but have you used these coding agents? They need it.

My point is that it shouldn't be necessary because the agent should already implement it.

I wish it did as well. I am sure someday, this tool won' t be needed. Until then... maybe it will!

Reply on news.ycombinator.com