跳到正文
Hacker News:AI 熱帖·· 4 天前AI 評分32

哈佛研究人員發現,AI 編碼智能體將瓶頸轉移至程式碼審查

Harvard researchers find AI coding agents shifted the bottleneck to code review

AI 導讀

哈佛研究人員發現,AI 編碼智能體提高程式碼產出後,瓶頸轉移至程式碼審查。Hacker News 討論中,有用戶指出,開發人員可能因自行提示及提交智能體生成的程式碼而跳過第二人審查,甚至不再仔細檢查輸出。

正文

Image 1Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Harvard researchers find AI coding agents shifted the bottleneck to code review (complexdiscovery.com) 23 points by judahmeek2 hours ago | hide | past | favorite | 28 comments help Image 2lz4003 minutes ago | next[–] 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 reply Image 3jacobgorm16 minutes ago | prev | next[–] 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 You could argue that the useful pingpong between coder and reviewers has been replaced by the similar pingpong between the prompter and the agent. reply Image 4prmoustache6 minutes ago | parent | next[–] 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. reply Image 5bambu2 minutes ago | parent | prev | next[–] 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 reply Image 6dominotw1 minute ago | prev | next[–] No pull request in my company get any human review comments anymore. No one is reading. reply Image 7dangoodmanUT18 minutes ago | prev | next[–] 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 reply Image 8michaelt7 minutes ago | parent | next[–] If someone doesn't think code review is the bottleneck, chances are they've got AI doing their code reviews too. reply Image 9fgblanch17 minutes ago | parent | prev | next[–] Harvard researchers found a tree in a forest reply Image 10gzell1 hour ago | prev | next[–] 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. reply Image 11donkey_brains23 minutes ago | parent | next[–] Very true. Which makes the conclusion reached be this study even worse: we are stuck reviewing endless PRs that solve the wrong problems. reply Image 12diego_moita2 minutes ago | parent | prev | next[–] 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. reply Image 13mathisfun12313 minutes ago | parent | prev | next[–] > 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. reply Image 14skydhash2 minutes ago | root | parent | next[–] 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... reply Image 15wewewedxfgdf14 minutes ago | prev | next[–] Test don't review. reply Image 16avereveard8 minutes ago | parent | next[–] That bottlenecks too, in startup ahead of the adoption curve the whole cicd pipeline down to how to merge is being rethought reply Image 17u1hcw9nx2 hours ago | prev | next[–] 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. reply Image 18judahmeek2 hours ago | prev | next[–] 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. reply Image 19ttctciyf11 minutes ago | prev | next[–] 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. reply Image 20ontouchstart10 minutes ago | prev | next[–] 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. reply Image 21jsrozner24 minutes ago | prev | next[–] We needed a research paper to tell us this? reply Image 22david-gpu16 minutes ago | parent | next[–] 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. reply Image 23aleqs11 minutes ago | root | parent | next[–] 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). reply Image 24hazbot22 minutes ago | parent | prev | next[–] A Havard research I'll have you know! /s reply Image 25aleqs17 minutes ago | parent | prev | next[–] do you even have a PhD? (/s) reply Image 26avereveard10 minutes ago | prev | next[–] Harward researcher read lovable blog post reply Image 27root_axis21 minutes ago | prev | next[–] I'm being told the answer is simply to let AI review and merge the code. Problem solved. reply Image 28dude25071112 minutes ago | parent | next[–] This, but unironically. reply Image 29wewewedxfgdf15 minutes ago | prev[–] But people keep saying "coding was never the bottleneck!". reply Image 30 Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search:

來源:Hacker News:AI 熱帖 · news.ycombinator.com