Interesting article, I'm generally sceptical of vibe engineering but Simon seems really balanced in his approach to it and in general his experiences line up with mine. AI can generally be outsourced to do two things - replace your thinking, and replace your typing, and I find the latter much more reliable.
Embracing the parallel coding agent lifestyle
71–80 of 147 posts
Re: Embracing the parallel coding agent lifestyle
#72Earlier quoted context omitted.
LLMs are literal gambling - you get them to work right once and they are magical - then you end up chasing that high by tweaking the model and instructions the rest of the time.
Or you put them to work with strong test suites and get stuff done. I am in bed. I have Claude fixing complex compiler bugs right now. It has "earned" that privilege by proving it can make good enough fixes, systematically removing actual, real bugs in reasonable ways by being given an immutable test suite and detailed instructions of the approach to follow. There's no gambling involved. The results need to be checke…
If you were an x86 assembly expert would you still feel the same way? (assuming you aren't already)
Re: Embracing the parallel coding agent lifestyle
#73The fact that we now have to write cook book about cook books kind of masks the reality that there is something that could be genuinely wrong about this entire paradigm. Why are even experts unsure about whats the right way to do something or even if its possible to do something at all, for anything non-trivial? Why so much hesitancy, if this is the panacea? If we are so sure then why not use the AI itself to come up…
Radioactivity was discovered before nuclear engineering existed. We had phenomena first and only later the math, tooling, and guardrails. LLMs are in that phase. They are powerful stochastic compressors with weak theory. No stable abstractions yet. Objectives shift, data drifts, evals leak, and context windows make behavior path dependent. That is why experts hedge. “Cookbooks about cookbooks” are what a field does w…
We’re in the alchemist phase. If I’m being charitable, the medieval stone mason phase.
One thing worth pointing out is that the pre-engineering building large structures phase lasted a long time, and building collapses killed a lot of people while we tried to work out the theory.
Also it wasn’t really the stone masons who worked out the theory, and many of them were resistant to it.
Re: Embracing the parallel coding agent lifestyle
#74Has anyone encountered any good YouTube channels that explore and showcase these workflows in a productive and educational manner?
Cole Medin have a few videos.
Re: Embracing the parallel coding agent lifestyle
#75The fact that we now have to write cook book about cook books kind of masks the reality that there is something that could be genuinely wrong about this entire paradigm. Why are even experts unsure about whats the right way to do something or even if its possible to do something at all, for anything non-trivial? Why so much hesitancy, if this is the panacea? If we are so sure then why not use the AI itself to come up…
LLMs are literal gambling - you get them to work right once and they are magical - then you end up chasing that high by tweaking the model and instructions the rest of the time.
LLMs are cargo cult generating machines. I’m not denying they can be useful for some tasks, but the amount of superstitions caused by these chaotic, random, black boxes is unreal.
Re: Embracing the parallel coding agent lifestyle
#76Along these lines, how does everyone visually organize the multiple terminal tabs open for these numerous agents in various states? I wish there were a way to search across all open tabs. I've started color-coding my Claude code tabs, all red, which helps me to find them visually. I do this with a preexec in my ~/.zshrc. But wondering if anyone else has any better tricks for organizing all of these agent tabs? I'm us…
Use tmux with multiple sessions. Then press Crtl-b S, you can interactively browse your seesons.
Re: Embracing the parallel coding agent lifestyle
#77There are quite a few products designed to help manage multiple agents at once. I'm trying out Conductor right now - https://conductor.build/ - it's a pretty slick macOS desktop app that handles running Claude Code within a GUI and uses Git worktrees to manage separate checkouts at the same time.
These apps are cool, but won't this functionality surely be replicated within Claude Code itself? This does seem to be in "picking up pennies in front of a steamroller" territory but I could be wrong.
Re: Embracing the parallel coding agent lifestyle
#78Earlier quoted context omitted.
If you really want your mind blown, see what Jesse is doing (successfully, which I almost can’t believe) with Graphviz .dot notation and Claude.md: https://blog.fsck.com/2025/09/29/using-graphviz-for-claudemd...
this is just 21st century voodoo
In a good sense or a bad one?
Re: Embracing the parallel coding agent lifestyle
#79My biggest hesitation about this is being stuck in merge hell. Even a minute or two needing to deal with that could negate the benefits of agents working in parallel. And I've tried some relatively simple rebase type operations with coding agents where they completely messed up. But if people are finding this is never an issue even with big diffs, I might be convinced to try it.