| ▲ | zeroonetwothree a day ago |
| Merely counting PRs is not very impressive to me. My pre LLM average is around 50/week anyway. But I’m not going to claim that somehow makes me the best programmer ever. I’m sure someone with 1 super valuable PR can easily create more value than I do. |
|
| ▲ | Terr_ a day ago | parent | next [-] |
| Maybe I'm just in a weird place, but I can't imagine 50 PRs a week. Maybe it's because I spend a lot of my time just turning problem reports reports on slack into tickets with tables of results and stack traces. |
| |
| ▲ | bdangubic a day ago | parent [-] | | automate that shit | | |
| ▲ | Terr_ a day ago | parent [-] | | Unfortunately its mostly B2B integration stuff, where the other end is another company which can sometimes be just as a quirky as a user, except at scale. "I received your spreadsheet detailing 821 records that are in State A but still haven't been moved to State B by our system as it adds Datapoint X on a regular basis. From what I can tell, it seems your data is missing crucial pieces you assured us would always be there. What's that? You want us to somehow fix whatever is somehow making those records in your AcmeERP system? Don't you have a support contract with that giant vendor? We seem like an easier target to hit up for impromptu tech-support consulting work? Well, I'll escalate that to the product manager..." |
|
|
|
| ▲ | wakawaka28 a day ago | parent | prev [-] |
| A bunch of tiny PRs is not hard to do manually. But LLMs can write boatloads of code to do kind of sophisticated things. You do have to figure out how to get to a point where you can trust the code. But the LLMs can help you write boatloads of tests too based on plain English descriptions. |
| |
| ▲ | 8note a day ago | parent [-] | | llms remove a lot of the difficulty of writing a ton of reasonable code, but is that really the bottleneck to producing a bunch of PRs? isn't it the reviewing time? reviewing code is hard work | | |
| ▲ | wakawaka28 a day ago | parent [-] | | Reviewing code can be hard but it's not as hard as writing the code. Even with the best autocomplete, and ergonomic editors like vim, it still takes quite a bit of time to write code for some features compared to the actual concepts being implemented. There are also lots of decisions like variable names that can be automated with a LLM. If you don't like what it came up with, you can tell it to change them. I recommend that you keep them fairly unique like you would for your own handwritten code, because ambiguity creates problems for people and machines alike. | | |
|
|
