alt Hacker NewsI think more people should focus on using LLMs to relieve cognitive load rather than parallelize and overload their brains. We need to learn to live with the fact that humans are not good at multi-tasking, and LLMs are not going to make us better at it.
I have started using Claude to develop an implementation plan, but instead of making Claude implement it and then have me spend time figuring out what it did, I simply tell it to walk me through implementing it by hand. This means that I actually understand every step of the development process and get to intervene and make different choices at the point of time where it matters. As opposed to the default mode which spits out hundreds of lines of code changes which overloads my brain, this mode of working actually feels like offloading the cognitive burden of keeping track of the implementation plan and letting me focus on both the details and the big picture without losing track of either one. For truly mechanical sub-tasks I can still save time by asking Claude to do them for me.
Replies
I love this idea! I'll try it today.
This resonates with me because I've been looking for a way to detect when I would make a different decision than the LLM. These divergence points generally happen because I'm thinking about future changes as I code, and the LLM just needs to pick something to make progress.
Prompts like "list your assumptions and do not write any code yet" help during planning. I've been experimenting with "list the decisions you've made during implementation that were not established upfront in the plan" after it makes a change, before I review it, because when eyeballing the diff alone, I often miss subtle decisions.
Thanks for sharing the suggestion to slow it down and walk the forking path with the LLM :)
Some of us love it, bit intense sometimes, but fun. So I guess we get to decide it ourselves what we prefer.
I know many will then say, BUT QUALITY, but if you learn to deal with your own and claude quirks, you also learn how to validate & verify more efficiently. And experience helps here.
I've been using a POC-driven workflow for my agentic coding.
What I do is to use the LLM to ask a lot of questions to help me better understand to problem. After I have a good understanding I jump into the code and code by hand the core of the solution. With this core work finished(keep in mind that at this point the code doesn't even need to compile) I fire up my LLM and say something like "I need to do X, uncommited in this repo we have a POC for how we want to do it. Create and implement a plan on what we need to do to finish this feature."
I think this is a good model because I'm using the LLM for the thing it is good at: "reading through code and explaining what it does" and "doing the grunt work". While I do the hard part of actually selecting the right way of solving a problem.