Why is reviewing hard? I use LLMs for reviewing. It is dogmatic to review every line written by an LLM.
always true to your name
Reviews have become expensive, rewrites have become cheap
21–30 of 82 posts
Re: Reviews have become expensive, rewrites have become cheap
#22Earlier quoted context omitted.
The simple sentences LLM keep generating break my brain, it's like 95% of writing is now 3rd grade level. Compare that to e.g. Martin Amis: https://en.wikiquote.org/wiki/Martin_Amis
Martin Amis level prose is neither possible nor desirable for a technical blog post.
Why?
Re: Reviews have become expensive, rewrites have become cheap
#23ai can do some of the reviewing, checking calling and called arguments, even things like crufty shell scripts. but the higher-level "should you do this?" or "check your design" - could AI do that stuff?
IMO it can, about as well as an entry/mid level dev
Re: Reviews have become expensive, rewrites have become cheap
#24ai can do some of the reviewing, checking calling and called arguments, even things like crufty shell scripts. but the higher-level "should you do this?" or "check your design" - could AI do that stuff?
> ai can do some of the reviewing
No way this can backfire.
> checking calling and called arguments
Like a static language compiler already does?
Re: Reviews have become expensive, rewrites have become cheap
#25Earlier quoted context omitted.
The simple sentences LLM keep generating break my brain, it's like 95% of writing is now 3rd grade level. Compare that to e.g. Martin Amis: https://en.wikiquote.org/wiki/Martin_Amis
Martin Amis level prose is neither possible nor desirable for a technical blog post.
I don't think that there is anything wrong with having stylistic depth in any wriitng
Re: Reviews have become expensive, rewrites have become cheap
#26ai can do some of the reviewing, checking calling and called arguments, even things like crufty shell scripts. but the higher-level "should you do this?" or "check your design" - could AI do that stuff?
> ai can do some of the reviewing No way this can backfire. > checking calling and called arguments Like a static language compiler already does?
I got to see greptile and it had a pretty decent code review, somewhat like a static analysis tool without a lot of time wasting nonsense/false positives.
When I've used static analysis tools, the first run is usually helpful as you cherry pick the things that need to be fixed, but then subsequent runs are just the false positives or "only slightly a nit" kind of annoyances.
But human developers are the ones that say stuff like "Do we really have to use a database at all?" etc...
Re: Reviews have become expensive, rewrites have become cheap
#27Writing blog posts has become cheap, making them sound human has become hard.
The simple sentences LLM keep generating break my brain, it's like 95% of writing is now 3rd grade level. Compare that to e.g. Martin Amis: https://en.wikiquote.org/wiki/Martin_Amis
> Style is not neutral; it gives moral directions.
> Nowadays every business in America says how warm it is and how much it cares — loan companies, supermarkets, hamburger chains.
Guess which one is AI and which one is a quote from Martin Amis.
Re: Reviews have become expensive, rewrites have become cheap
#28Failures in production remain expensive.
I wish they were.
Displaying an error message to the user, asking to try again later, is way too cheap in my opinion.
Re: Reviews have become expensive, rewrites have become cheap
#29Writing blog posts has become cheap, making them sound human has become hard.
The simple sentences LLM keep generating break my brain, it's like 95% of writing is now 3rd grade level. Compare that to e.g. Martin Amis: https://en.wikiquote.org/wiki/Martin_Amis
That's not just you imagining things, that's the world around you changing. That's real and it matters.
Re: Reviews have become expensive, rewrites have become cheap
#30ai can do some of the reviewing, checking calling and called arguments, even things like crufty shell scripts. but the higher-level "should you do this?" or "check your design" - could AI do that stuff?
It's difficult to spot issues from a huge diff.
But when a agent finish a task, it remembers what it just went through, where it got stuck, when it got corrected by human, what code make it want to say the F word to the author, that would be a good chance to make the codebase cleaner.