| ▲ | pinkgolem a day ago |
| What really important things are human reviews catching in your org? I just feel more and more like the effort invested in manual reviews is not worth it |
|
| ▲ | grokys a day ago | parent | next [-] |
| 1. Whether the thing should be done in the first place 2. If it's the correct solution on a high level 3. Whether it conflicts with or duplicates other parts of the system 4. Whether the comments are actually useful or restating the LLM chat Also many others but these are the most common IME |
| |
| ▲ | 9dev a day ago | parent [-] | | All of these are angles an AI reviewer can test for as well, and will (IME) mostly catch mistakes correctly. I also still manually review code, and usually also catch issues, but the severity of what I find shrinks ever further as agents get better. The sprawling code comments are becoming the most draining part of code review though, that's really killing me from the inside. | | |
| ▲ | embedding-shape a day ago | parent | next [-] | | > All of these are angles an AI reviewer can test for as well, and will (IME) mostly catch mistakes correctly. No, none of today's AI would give you enough signal around "should this thing be built in the first place" nor if it's the correct solution on a high level. They don't understand why you are doing what you are doing, and even if you explain it, they still don't actually understand the motivation and lots of other things. You'll get them to do guesses and pretend they actually know how to prioritize and will tell you it makes lots of sense, whatever they come up with. But try following it blindly and you'll see where you end up. This is why "one agent + one good developer" beats "thousands of agents working in a swarm" still today. | | |
| ▲ | 9dev a day ago | parent [-] | | I don’t think I claimed agent reviews to be a panacea. It’s a tool that can help you lower the review pressure in companies working with agentic coding tools. | | |
| ▲ | embedding-shape a day ago | parent [-] | | Someone asked: > What really important things are human reviews catching in your org? Another person said: > 1. Whether the thing should be done in the first place And you replied: > All of these are angles an AI reviewer can test for as well, and will (IME) mostly catch mistakes correctly Which as I noted, is very far from the truth. I neither claimed that you said "agent reviews are a panacea", but when you claim "AI can solve all those things" and two of the first items cannot be addressed by AI (today), then I'm rebuking those specific things, not some other general point you implicitly made. | | |
| ▲ | 9dev a day ago | parent [-] | | But that’s the thing, when I say "mostly" that sure doesn’t imply it can solve all those things - it can help to a great extent. | | |
| ▲ | embedding-shape a day ago | parent [-] | | It is mostly useless at figuring out if "should this thing be built in the first place" and "if it's the correct solution", and mostly cannot help at all with those things. Where "mostly" means kind of what it says but also not really. |
|
|
|
| |
| ▲ | Paria_Stark a day ago | parent | prev [-] | | The AI review are still quite far from having the same level of critical thinking and high level knowledge of your application, what you have done in the past and want to do next etc. If you don't master this for your own project, what's even the point of your job. |
|
|
|
| ▲ | rhdunn a day ago | parent | prev [-] |
| 1. Does the implementation fit in the architecture/style of the project? 2. Are there potential security, accessibility, performance, etc. issues? 3. Domain specific knowledge (SQL, ASP.NET, XQuery, etc.) where there are better ways of solving a problem, or possible issues not handled. 4. Sense checking ... is the code easy to read? does it need an explanatory comment? does it need named parameters? etc. |
