101–106 of 106 posts
For me it’s OK because I deliberately reduces AI usage even for boilerplate stuffs. My daily loc is around a few hundred.
Earlier quoted context omitted.
> Like using feature/xxxxx as the branch name. Last year exactly zero developers used this convention. People have been doing this for years.
> People have been doing this for years. Tell me something I don't know. My point is that it's usage has seen a _measurable_ increase where I work over the last two years. I don't think I have a single "feature/*" branch before 2024. Developer names, feature names, sure. But specifically feature/, no.
> I don't think I have a single "feature/*" branch before 2024.
You might not, but other people have. Just because you haven't seen something doesn't mean it doesn't exist. Don't assume that your personal experience is representative of the whole world of software.
Earlier quoted context omitted.
> and so has the output quality Not my experience at all. The quality has gone up dramatically . Because we also use LLMs to make large scale refactorings that cleans up the code and use it to find lots of bugs that would otherwise have exploded in production at some point in time.
I just used Fable to thoroughly review a PR, and it came up with 5 "Findings that block approval". I went through each one through the code path (a couple were already considered during implementation), and while all 5 were theoretically accurate, 0 of them were actually reachable. I wrote them back to Claude point by point and got this back: "I checked all five claims against the code. Your list is correct on all fi…
For example, a few weeks ago I asked it to analyse my code and find duplicated code that could be extracted into reusable libraries. It found several good examples and did the refactoring. I reviewed the result, and it was 100% how I would have coded it myself.
I do almost no manual coding these days. Opus 5 just works for me.
So it is strange for me to read comments like yours saying that it doesn't work. It would be interesting to find out what makes the difference?
Earlier quoted context omitted.
I just used Fable to thoroughly review a PR, and it came up with 5 "Findings that block approval". I went through each one through the code path (a couple were already considered during implementation), and while all 5 were theoretically accurate, 0 of them were actually reachable. I wrote them back to Claude point by point and got this back: "I checked all five claims against the code. Your list is correct on all fi…
This!! the amount of times that has happened to me in PR. A lot of the times its my fault as I haven't given the agent all of the context ( sometimes intentionally to cross check if it would reach to the same conclusion as me without additional info) but as soon as I give it all the context it would then back track on most of the blockers.
I use Opus 5 every day, and it just works. It is very rare that I need to do any manual editing.
Earlier quoted context omitted.
I just used Fable to thoroughly review a PR, and it came up with 5 "Findings that block approval". I went through each one through the code path (a couple were already considered during implementation), and while all 5 were theoretically accurate, 0 of them were actually reachable. I wrote them back to Claude point by point and got this back: "I checked all five claims against the code. Your list is correct on all fi…
That is interesting. I use Opus 5 as my daily driver, and it pretty much just works. For example, a few weeks ago I asked it to analyse my code and find duplicated code that could be extracted into reusable libraries. It found several good examples and did the refactoring. I reviewed the result, and it was 100% how I would have coded it myself. I do almost no manual coding these days. Opus 5 just works for me. So it…
For what it's worth I/we do much less manual coding now too, but it almost always takes a handful of re-prompts to reach expectations.
We can do hooks to reduce superfluous comments or do a second specs-adherence pass, or write failing tests first, but other discrepancies aren't uniform enough to enforce in prompts or context.
I'd love to know the difference too. Or whether long term velocity would be higher by vibing through PRs and deal with issues when things explode or refactor down 2M lines of LLM creep after the fact.