Rendered at 06:56:57 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
tabs_or_spaces 44 seconds ago [-]
> LLMs aren’t lazy. They don’t cut corners because a simpler solution feels good enough. If they know how to solve something thoroughly, they will.
This is a severe misunderstanding in how LLMs work..
I don't know how this got on my front page....
SCdF 1 hours ago [-]
> LLMs aren’t lazy. They don’t cut corners because a simpler solution feels good enough. If they know how to solve something thoroughly, they will.
I don't know why they think this, but no? Perhaps it's badly expressed, but LLMs cut corners all the time. It's sort of their core fault really.
Anyway, I disagree with the core premise[1]. Re-writes are not cheap, because 1) code can be so bad it's unclear how to rewrite it[2], b) code can be so significant it's challenging to rewrite it (architectural choices, schemas, etc), and lastly if you're ever wanting to own your own code and not rent it from LLM companies, having it understandable by a human is still a goal worth working toward.
[1] To be fair, I think OP _might_ be talking about rewriting in the moment of the thing being built, but with some unspoken rule that once they think the change is good enough, then they are reviewing all the code? They don't make it clear..
[2] it's not even that hard. Write a test that exercises an end result and not the rule that causes that end result and 6 months later you've forgotten why the code is like that. I had to maintain a piece of software once where the primary form of tests were a bunch of snapshots of an end report being generated, based on some initial data input, mostly all unlabeled. The code was like "do this SQL query on table A and then take the second result". Why the second result? Your guess is as good as mine! I couldn't even work out why they were querying table A and not table B...
saidinesh5 3 hours ago [-]
We faced a lot of this this year. Eager new joinees sent 100s of lines of CLs to review to "improve" little things.
Not only did the new changes did not fix what they thought it would fix but it broke other things in unexpected ways.
I brought in two changes after that:
* I'm not reviewing/reading anything that you yourself did not read / test in the target environments properly. If all it takes is an LLM prompt, I could be issuing the same prompt to make my life easier.. and If you're sending a CL, you should be owning the code you send.
* Me being more involved in the design process so review burden itself becomes lower. A bit of pair programming from time to time helped too.
Not sure how things will turn out after this but so far they seem better.
usernametaken29 2 hours ago [-]
> The shortest path for the model is to implement it completely
Have you worked with LLMs???????????
“I disabled the test so it’s not run so now all the tests pass” is not a hypothetical it’s pretty common. LLMs frequently do shortcut learning. The reason why reviews are expensive is because you still need to do all the steps in order to understand if a shortcut is justified.
nomel 2 hours ago [-]
> “I disabled the test so it’s not run so now all the tests pass”
Also:
"I implemented it this terrible way because of precedence in the codebase...that I just wrote"
"I avoided implementing this correctly because of migration concern for existing installations of this code I'm writing right now"
"I deferred this critical feature for the future, so we can deploy quicker"
or, my favorite,
"I hand rolled an buggy http server because you said the tool should be self contained"
bot403 2 hours ago [-]
Or bizarrely Claude askes about code churn like it matters.
Human, Do you want me to do it the right way? It will cause code churn in 90 files. Or I can take a shortcut and edit 3 files in a terrible way.
Edits 90 files for 12 lines each in 25 seconds...
tobyhinloopen 53 minutes ago [-]
“This is a significant rewrite that will take weeks”
Done after my potty break
bcrosby95 2 hours ago [-]
I used Fable to write a relatively small RPG. In the span of 2 hours it managed to do many interesting things. My favorite was when it wrote code with a race condition that could cause people to take more damage than they should, which it then defended as an acceptable tradeoff for parallelism.
dap 4 hours ago [-]
If your plan is to not review and just have the LLM rewrite if it doesn’t work, it doesn’t sound like the rewrite is gonna be any better.
nnevatie 6 minutes ago [-]
As explained by a LLM.
dmitrig01 5 hours ago [-]
Writing blog posts has become cheap, making them sound human has become hard.
netsharc 5 hours ago [-]
The simple sentences LLM keep generating break my brain, it's like 95% of writing is now 3rd grade level.
That's not just you imagining things, that's the world around you changing. That's real and it matters.
jamesknelson 2 hours ago [-]
So reading this, I know it’s probably a human posing as an LLM. But the problem with formats like this is that I don’t actually know.
If a human said this to me in real life, and I laughed, it would probably help build a connection with that person, as it’s signaling that we have in common an unusually strong grasp of the patterns in LLM output (unusually strong at least in comparison to the general population).
But here? I don’t gain anything by reading this comment. It only contributes to the uncertainty that anything I read on this site has any meaning at all.
Please, if you’re a human, don’t mimic LLMs on forums where the reader cannot distinguish you from an LLM without doing investigative work.
And you’re an LLM, please report to your owner that he is an ass for polluting one of the last bastions of high entropy discussion on the information superhighway.
bartvk 1 hours ago [-]
Please add a /s if appropriate.
duggan 9 minutes ago [-]
Takes all the fun out of it.
girvo 3 hours ago [-]
You could even argue that it’s the load-bearing point!
defen 4 hours ago [-]
Martin Amis level prose is neither possible nor desirable for a technical blog post.
DiscourseFan 4 hours ago [-]
I don't think that there is anything wrong with having stylistic depth in any wriitng
ShinyLeftPad 4 hours ago [-]
Why?
gobdovan 3 hours ago [-]
> 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.
rogerrogerr 2 hours ago [-]
Without looking, I’m guessing one of these was cherry-picked from Amis and one was plucked nearly at random from LinkedIn.
The writing style AI uses has its place, but not as _every sentence_. That’s what is exasperating. At the same time, I’m happy that I can still at least identify AI prose of more-than-trivial length.
3 hours ago [-]
geraneum 3 hours ago [-]
> An LLM defaults to building when it should be buying. Not because it doesn’t know about existing libraries, it often mentions them, but because for an LLM, writing two hundred lines of implementation is the same cognitive effort as writing two lines of import.
Or maybe they are trained that way. It’s more tokens used and more money you need to pay.
hintymad 2 hours ago [-]
Shouldn't we really consider review and rewrite together? If so, the economics may not change as drastically[1]. It's just like writing code by hand: we spend lots of time organizing our thoughts and examining our code, which is not that different from reviewing.
[1] Unless you're an engineer in Anthropic, so you just spend you time writing "loop".
eschneider 5 hours ago [-]
Failures in production remain expensive.
rixed 3 hours ago [-]
I wish they were.
Displaying an error message to the user, asking to try again later, is way too cheap in my opinion.
Analemma_ 3 hours ago [-]
Do they, though? AWS and CloudFlare recently had the worst outages in their history, and GitHub is flirting with zero nines of uptime these days. Doesn’t seem to have cost them any business.
zarzavat 7 minutes ago [-]
An outage is the best failure that can happen. The worst that can happen depends on the system but could be anything from a business collapsing because of an attack, your production database being stolen and wiped, all the way to someone dying.
drudolph914 2 hours ago [-]
I’ve personally reached a point where if I’m saving time typing, but gaining back that time on reviewing and understanding, I may as well have just written the code most of the time. AI is great for boilerplate and learning, but my team has given up on trying to use the tool for entire implementations
m463 5 hours ago [-]
ai 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?
lericzhang 3 hours ago [-]
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.
ShinyLeftPad 4 hours ago [-]
> ai can do some of the reviewing
No way this can backfire.
> checking calling and called arguments
Like a static language compiler already does?
m463 4 hours ago [-]
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...
shepherdjerred 4 hours ago [-]
IMO it can, about as well as an entry/mid level dev
ares623 5 hours ago [-]
I think the question is now "should you care?" And it seems the magnificent, incorruptible thought leaders of our time are all converging on "No"
2 hours ago [-]
5 hours ago [-]
hluska 5 hours ago [-]
I’m not sure I agree with this or maybe I don’t understand. In my experience, the over engineered code LLMs create have more big problems. Rewriting vast parts of code when I have an outage or need a new feature means the code evolves far faster than my understanding. That gets more and more dangerous. Or maybe I’m not smart enough to follow the new pace?
bryanlarsen 4 hours ago [-]
AFAICT, the author is talking about rewriting code during a review as part of the review process.
quote: "If I identify code that’s more complex than it needs to be, in my own work or in someone else’s PR"
If so, that makes a lot of sense to me. The best time to rewrite code is before it hits production.
joshka 5 hours ago [-]
[flagged]
5 hours ago [-]
simianwords 5 hours ago [-]
Why is reviewing hard? I use LLMs for reviewing. It is dogmatic to review every line written by an LLM.
bryanlarsen 5 hours ago [-]
LLM's are good at some types of reviews and awful at others. They generally tend to overcomplicate things and miss opportunities to simplify. They pretty much have to take pre-existing code and tests as gospel and cannot distinguish which is buggy, incomplete, unimportant or important. They have no knowledge of unwritten business requirements, customer preferences, et cetera so high level review is always necessary.
simianwords 32 minutes ago [-]
Yeah ok but that’s what I have. I have the knowledge of unwritten business requirements and customer preferences.
My knowledge + Claude is much better than just my knowledge
CBLT 5 hours ago [-]
I also like having long, pointed conversations with LLMs as I review code. Then when I'm done, it's different code, and it has all of my blind spots and knowledge gaps, so I cannot effectively review it anymore.
It's like turning a code review that requests you, into a code review that requests someone else. And it tramples on the original author quite a bit too. It's hard only having the ability to add incremental value to large amounts of code, instead of large amounts of value to incremental code.
happytoexplain 5 hours ago [-]
I'm confused - are you purposefully pretending that the author isn't talking about human review?
gravypod 5 hours ago [-]
What kind of systems do you work on? Does it have production traffic? Is there a cost to downtime?
g-b-r 4 hours ago [-]
always true to your name
cyanydeez 5 hours ago [-]
you arnt reviewing. youre playing loophole semantics.
This is a severe misunderstanding in how LLMs work..
I don't know how this got on my front page....
I don't know why they think this, but no? Perhaps it's badly expressed, but LLMs cut corners all the time. It's sort of their core fault really.
Anyway, I disagree with the core premise[1]. Re-writes are not cheap, because 1) code can be so bad it's unclear how to rewrite it[2], b) code can be so significant it's challenging to rewrite it (architectural choices, schemas, etc), and lastly if you're ever wanting to own your own code and not rent it from LLM companies, having it understandable by a human is still a goal worth working toward.
[1] To be fair, I think OP _might_ be talking about rewriting in the moment of the thing being built, but with some unspoken rule that once they think the change is good enough, then they are reviewing all the code? They don't make it clear..
[2] it's not even that hard. Write a test that exercises an end result and not the rule that causes that end result and 6 months later you've forgotten why the code is like that. I had to maintain a piece of software once where the primary form of tests were a bunch of snapshots of an end report being generated, based on some initial data input, mostly all unlabeled. The code was like "do this SQL query on table A and then take the second result". Why the second result? Your guess is as good as mine! I couldn't even work out why they were querying table A and not table B...
Not only did the new changes did not fix what they thought it would fix but it broke other things in unexpected ways.
I brought in two changes after that:
* I'm not reviewing/reading anything that you yourself did not read / test in the target environments properly. If all it takes is an LLM prompt, I could be issuing the same prompt to make my life easier.. and If you're sending a CL, you should be owning the code you send.
* Me being more involved in the design process so review burden itself becomes lower. A bit of pair programming from time to time helped too.
Not sure how things will turn out after this but so far they seem better.
Have you worked with LLMs??????????? “I disabled the test so it’s not run so now all the tests pass” is not a hypothetical it’s pretty common. LLMs frequently do shortcut learning. The reason why reviews are expensive is because you still need to do all the steps in order to understand if a shortcut is justified.
Also:
"I implemented it this terrible way because of precedence in the codebase...that I just wrote"
"I avoided implementing this correctly because of migration concern for existing installations of this code I'm writing right now"
"I deferred this critical feature for the future, so we can deploy quicker"
or, my favorite,
"I hand rolled an buggy http server because you said the tool should be self contained"
Human, Do you want me to do it the right way? It will cause code churn in 90 files. Or I can take a shortcut and edit 3 files in a terrible way.
Edits 90 files for 12 lines each in 25 seconds...
Done after my potty break
Compare that to e.g. Martin Amis: https://en.wikiquote.org/wiki/Martin_Amis
If a human said this to me in real life, and I laughed, it would probably help build a connection with that person, as it’s signaling that we have in common an unusually strong grasp of the patterns in LLM output (unusually strong at least in comparison to the general population).
But here? I don’t gain anything by reading this comment. It only contributes to the uncertainty that anything I read on this site has any meaning at all.
Please, if you’re a human, don’t mimic LLMs on forums where the reader cannot distinguish you from an LLM without doing investigative work.
And you’re an LLM, please report to your owner that he is an ass for polluting one of the last bastions of high entropy discussion on the information superhighway.
> 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.
The writing style AI uses has its place, but not as _every sentence_. That’s what is exasperating. At the same time, I’m happy that I can still at least identify AI prose of more-than-trivial length.
Or maybe they are trained that way. It’s more tokens used and more money you need to pay.
[1] Unless you're an engineer in Anthropic, so you just spend you time writing "loop".
but the higher-level "should you do this?" or "check your design" - could AI do that stuff?
No way this can backfire.
> checking calling and called arguments
Like a static language compiler already does?
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...
quote: "If I identify code that’s more complex than it needs to be, in my own work or in someone else’s PR"
If so, that makes a lot of sense to me. The best time to rewrite code is before it hits production.
My knowledge + Claude is much better than just my knowledge
It's like turning a code review that requests you, into a code review that requests someone else. And it tramples on the original author quite a bit too. It's hard only having the ability to add incremental value to large amounts of code, instead of large amounts of value to incremental code.