HN Explorer

Coding assistants are slow. So we multitask

4 points by brunaxLorax ↗ HN
Coding assistants are slow.

Obviously they are extremely fast in comparison to the best human programmers, but they are still too slow to be our one-to-one enhanced pair programmer. Our current solution is multi-instances, toggling between tasks. However, Multitasking is known to be a poor method, with low productivity and causing harm as it increases cognitive load, stress and fatigue levels.

I am sure that this is temporary and we will soon have coding assistants fast enough for deep focus on single tasks. What do you think?

3 comments

[ 1.9 ms ] story [ 17.4 ms ] thread
PaulHoule
Personally I'm careful about multitasking. If you had two agents working on things in parallel you are going to have more problems stomping on each other's work even if they are working in two different checkouts of the same code. Also in terms of your effort supervising them if you are going back from one to the other you're more likely to get confused.

I wouldn't say "never multitask" but I think you should think carefully about a portfolio of things you can work on that don't conflict with each other.

One possibility to to race analysis of situations with an LLM. For instance punch in a prompt asking if it can figure out the cause of a bug and go off and try figuring it out yourself in the debugger. Or read or write documentation when it is off on a mission.

tjr
Genuinely curious: how quickly do you need new code written? What kinds of things are you working on that still aren’t being done fast enough?
brunaxLorax
I recently came across https://claudecode.run/ (not affiliated). There are currently several similar products that help that multi-instance Claude Code layout