A lot of this university research on AI feels dated. This is something we all faced months ago. Many times they're also reaching conclusions using obsolete models, etc. Feels like things move too fast for traditional research cycles to catch up to AI dev
The problem is that when nobody writes code or feels ownership over it anymore, nobody will be qualified to or really interested in doing the code reviews. The way forward could involve dropping code reviews altogether. You could argue that the useful pingpong between coder and reviewers has been replaced by the similar pingpong between the prompter and the agent.
In my company, people found out that if they use an agent that commits and do the pull/merge request, they can approve it themselves and bypass a second set of eyes.
Since they are the one doing the prompting, they quickly got lazy of actually reviewing the output from the LLM which means that nobody is reviewing anything.
It hasn't happened yet but I guess that is how you end up with major outages.
That would be great, IF there were valuable ping-pong between the prompter and the agent. For skilled engineers the game between themselves and the agent is enough. But most people are submitting senseless slop grenades for review.
Claude always comes up with more things to add to the code that are pure bloat and become inbred bombs over several iterations, and some people can't distinguish what suggestions to reject and go along with everything Claude suggests to the detriment of the program #garrytangate
From real-world experience, I have to disagree. It always has been and continues to be a faulty, up-front specification problem. The tail don't wag the dog.
If I increased the output of my pump jack and identified the refinery as the new bottleneck would you say the same pithy thing? NB a single pump jack can pump different grades of crude oil at the same time.
This again increases the demand for good programmers.
Write only programmers are dime on dozen. Those who can read code written by others (and themselves) and analyze it are harder to find.
I've submitted the original paper (https://fion.ac/jellyfish.pdf), but others already have to little engagement, likely due to the paper's terrible title.
Vaguely reminiscent of the classic trope around 70's computer "effficiency gains" where a newly introduced computerised accounting system would end up taking longer than the original human-run system because once the computer was through doing the books the original human bookkeeper must still check the results manually.
And just because harvard researchers say something doesn't make it true either. Especially when it's like 6 months late and reviews are probably not the bottleneck anymore - testing, ci, parallelization are (imo).
A lot of this university research on AI feels dated. This is something we all faced months ago. Many times they're also reaching conclusions using obsolete models, etc. Feels like things move too fast for traditional research cycles to catch up to AI dev
The problem is that when nobody writes code or feels ownership over it anymore, nobody will be qualified to or really interested in doing the code reviews. The way forward could involve dropping code reviews altogether. You could argue that the useful pingpong between coder and reviewers has been replaced by the similar pingpong between the prompter and the agent.
In my company, people found out that if they use an agent that commits and do the pull/merge request, they can approve it themselves and bypass a second set of eyes.
Since they are the one doing the prompting, they quickly got lazy of actually reviewing the output from the LLM which means that nobody is reviewing anything.
It hasn't happened yet but I guess that is how you end up with major outages.
That would be great, IF there were valuable ping-pong between the prompter and the agent. For skilled engineers the game between themselves and the agent is enough. But most people are submitting senseless slop grenades for review.
Claude always comes up with more things to add to the code that are pure bloat and become inbred bombs over several iterations, and some people can't distinguish what suggestions to reject and go along with everything Claude suggests to the detriment of the program #garrytangate
No pull request in my company get any human review comments anymore. No one is reading.
This feels obvious to me, but it's interesting how so many people feel the opposite.
I guess it depends a lot on how a company manages their SDLC/bureaucracy
If someone doesn't think code review is the bottleneck, chances are they've got AI doing their code reviews too.
Harvard researchers found a tree in a forest
From real-world experience, I have to disagree. It always has been and continues to be a faulty, up-front specification problem. The tail don't wag the dog.
Very true. Which makes the conclusion reached be this study even worse: we are stuck reviewing endless PRs that solve the wrong problems.
I don't fully disagree with you. That is a real big problem.
But both things can be true. One problem doesn't exclude the other.
> The tail don't wag the dog
If I increased the output of my pump jack and identified the refinery as the new bottleneck would you say the same pithy thing? NB a single pump jack can pump different grades of crude oil at the same time.
You may need to check the pipeline so that the refinery isn't stuck filtering random stuff from the oil.
AKA, it would be nice to have nice patches like this one to review.
https://cgit.freebsd.org/src/commit/?id=09d62ba33de113d01e88...
Test don't review.
That bottlenecks too, in startup ahead of the adoption curve the whole cicd pipeline down to how to merge is being rethought
This again increases the demand for good programmers. Write only programmers are dime on dozen. Those who can read code written by others (and themselves) and analyze it are harder to find.
I've submitted the original paper (https://fion.ac/jellyfish.pdf), but others already have to little engagement, likely due to the paper's terrible title.
Vaguely reminiscent of the classic trope around 70's computer "effficiency gains" where a newly introduced computerised accounting system would end up taking longer than the original human-run system because once the computer was through doing the books the original human bookkeeper must still check the results manually.
I have never heard of the term Job Market Paper (JMP) but this is the second one I saw on HN in two days. The other one is this
https://news.ycombinator.com/item?id=50516245
Guess I have to ask AI.
We needed a research paper to tell us this?
Just because it is obviously true to you, it doesn't mean it is obviously true to others.
And just because it is obviously true to you, it doesn't mean that it is true, either.
And just because harvard researchers say something doesn't make it true either. Especially when it's like 6 months late and reviews are probably not the bottleneck anymore - testing, ci, parallelization are (imo).
A Havard research I'll have you know! /s
do you even have a PhD?
(/s)
Harward researcher read lovable blog post
I'm being told the answer is simply to let AI review and merge the code. Problem solved.
This, but unironically.
But people keep saying "coding was never the bottleneck!".