Comment by danenania
2 days ago
I know of many experienced and capable engineers working on complex stuff who are driving basically all their development through agents. This includes production level work. This is the norm now in the SV startup world at least.
You don't just YOLO it. You do extensive planning when features are complex, and you review output carefully.
The thing is, if the agent isn't getting it to the point where you feel like you might need to drop down and edit manually, agents are now good enough to do those same "manual edits" with nearly 100% reliability if you are specific enough about what you want to do. Instead of "build me x, y, z", you can tell it to rename variables, restructure functions, write specific tests, move files around, and so on.
So the question isn't so much whether to use an agent or edit code manually—it's what level of detail you work at with the agent. There are still times where it's easier to do things manually, but you never really need to.
Can you show some example? I feel like there would be streams or YouTube lets plays on this if it was working well
I would like to see it as well. It seems to me that everybody sells shovels only. But nobody haven’t seen gold yet. :)
The real secret to agent productivity is letting go of your understanding of the code and trusting the AI to generate the proper thing. Very pro agent devs like ghuntley will all say this.
And it makes sense. For most coding problems the challenge isn’t writing code. Once you know what to write typing the code is a drop in the bucket. AI is still very useful, but if you really wanna go fast you have to give up on your understanding. I’ve yet to see this work well outside of blog posts, tweets, board room discussions etc.
> The real secret to agent productivity is letting go of your understanding of the code and trusting the AI to generate the proper thing
The few times I've done that, the agent eventually faced a problem/bug it couldn't solve and I had to go and read the entire codebase myself.
Then, found several subtle bugs (like writing private keys to disk even when that was an explicit instruction not to). Eventually ended up refactoring most of it.
It does have value on coming up with boilerplate code that I then tweak.
2 replies →
That's just irresponsible advice. There is so little actual evidence of this technology being able to produce high quality maintainable code that asking us to trust it blindly is borderline snake-oil peddling.
3 replies →
I don’t see how I would feel comfortable pushing the current output of LLMs into high-stakes production (think SLAs, SRE).
Understanding of the code in these situation is more important than the code/feature existing.
3 replies →
> The real secret to agent productivity is letting go of your understanding of the code
This is negligence, it's your job to understand the system you're building.
Not to blow your bubble, but I've seen agents expose Stripe credentials by hardcoding them as text into a react frontend app, so, no kids, do not "let go" of code understanding, lest you want to appear as the next story along the lines of "AI dropped my production database".
This is sarcasm right?
2 replies →
A lot of that would be people working on proprietary code I guess. And most of the people I know who are doing this are building stuff, not streaming or making videos. But I'm sure there must be content out there—none of this is a secret. There are probably engineers working on open source stuff with these techniques who are sharing it somewhere.
That’s understandable, I also wouldn’t stream my next idea for everyone to see
Let’s see it then
2 replies →
+1 here. Lets see those productivity gains!