> ..._massive_ boost to productivity. ~20% of the commits to the OpenHands codebase are now authored or co-authored by OpenHands itself.
I'm having trouble reconciling these statements. Where does the productivity boost come from since that reviewing burden seems much greater than you'd have if you knew commits were coming from a competent human?
Because the burden is much lower than if you were authoring the same commit yourself without any automation?
I think this is why people struggle so much with agents--they see the agent perform magic, then assume it can be trusted with a larger task, where it completely falls down.
If the cost is small to setting a coding agent (e.g. aider) on a task, seeing if it reaches a quick solution, and just aborting if it spins out, you can solve a subset of these types of issues very quickly, instead of leaving them in issue tracking to grow stale. That lets you up the polish on your work.
That's still quite a different story to having it do the core, most important part of your work. That feels a little further away. One of the challenges is the scout rule, the refactoring alongside change that makes the codebase nicer. I feel like today it's easier to get a correct change that slightly degrades codebase quality, than one that maintains it.
Merge conflicts are probably the biggest one for me. I put up a PR and move onto a new task. Someone approves, but now there are conflicts. I could switch off my task, spend 5-10 min remembering the intent of this PR and fixing the issues. Or I could just say "@openhands fix the merge conflicts" and move back to my new task.
Playing the other side, pipelining is real.
I imagine the same thing applies to agents. You can waste a lot of time by giving them tasks that are beyond them and then having to review complicated work that is more likely to be wrong than right. But once you develop an intuition for what they can and cannot do you can act appropriately.
Claude 3.5 is not bad really. I wanted to do a side project that has been on my mind for a few years, and Claude coded it in like 30 seconds.
So to say "we are not even close" seems strange. If LLMs continue to improve, they will be comparable to mid level developers in 2-3 years, senior developers in 4-5 years.
These sorts of things can’t be extrapolated. It could be 6-months, it could be a local maxima / dead end that’ll take another breakthrough in 10 years like transformers were. See self-driving cars.
My experience is acctually they’ve become dramatically less helpful over the past two years (past year in particular). Claude seems not to have backslid much but it’s progression also has not been very fast at all (I’ve noticed no difference since the 3.5 launch despite several updates).
Everything grows sinusoidally and I feel we’re well past the tipping point into diminishing rate of improvement
It can seem great for certain tasks at first. Yesterday I had to add license headers to the top of a lot of source code files. The reason why I let the AI try is because the repository contained lots of different programming languages.
It was able to do this but I then realized that it just removed the last sentence of the text it was supposed to add.
We are not even close to the point where AI can "replace" a software engineer. Their code still needs to be reviewed and tested, at least as much as you'd scrutinize the code of a brand new engineer just out of boot camp. I've talked to companies who went all in on AI engineers, only to realize two months later that their codebase was rotting because no one was reviewing the changes.
But once you develop some intuition for how to use them, software agents can be a _massive_ boost to productivity. ~20% of the commits to the OpenHands codebase are now authored or co-authored by OpenHands itself. I especially love asking it to do simple, tedious things like fixing merge conflicts or failing linters. It's great at getting an existing PR over the line.
It's also important to keep in mind that these agents are literally improving on a _weekly_ basis. A few weeks ago we were at the top of the SWE-bench leaderboard; now there are half a dozen agents that have pulled ahead of us. And we're one launch away from leapfrogging back to the top. Exciting times!
https://github.com/All-Hands-AI/OpenHands