llm/5888b8dc-b96e-4444-9c3c-465dde409e92/topic-5-0a1e9699-3906-4a23-9644-b7f7d5fa465b-input.json
You are a comment summarizer. Given a topic and a list of comments tagged with that topic, write a single paragraph summarizing the key points and perspectives expressed in the comments. TOPIC: Code review burden with AI COMMENTS: 1. Why train to pedal fast when we already got motorcycles? You are preparing for yesterday's needs. There will never be a time when we need to solve this manually like it's 2019. Even in 2019 we would probably have used Google, solving was already based on extensive web resources. While in 1995 you would really have needed to do it manually. Instead of manual coding training your time is better invested in learning to channel coding agents, how to test code to our satisfaction, how to know if what AI did was any good. That is what we need to train to do. Testing without manual review, because manual review is just vibes, while tests are hard. If we treat AI-generated code like human code that requires a line-by-line peer review, we are just walking the motorcycle. How do we automate our human in the loop vibe reactions? 2. > Instead of manual coding training your time is better invested in learning to channel coding agents All channelling is broken when the model is updated. Being knowledgeable about the foibles of a particular model release is a waste of time. > how to test code to our satisfaction Sure testing has value. > how to know if what AI did was any good This is what code review is for. > Testing without manual review, because manual review is just vibes Calling manual review vibes is utterly ridiculous. It's not vibes to point out an O(n!) structure. It's not vibes to point out missing cases. If your code reviews are 'vibes', you're bad at code review > If we treat AI-generated code like human code that requires a line-by-line peer review, we are just walking the motorcycle. To fix the analogy you're not reviewing the motorcycle, you're reviewing the motorcycle's behaviour during the lap. 3. $20 is fine. I used a free trial before Christmas, and my experience was essentially that my code review speed would've prevented me doing more than twice that anyway… and that's without a full time job, so if I was working full time, I'd only have enough free time to review $20/month of Claude's output. You can vibe code, i.e. no code review, but this builds up technical debt. Think of it as a junior who is doing one sprint's worth of work every 24 hours of wall-clock time when considering how much debt and how fast it will build up. 4. Yeah, this is a lot of what I'm doing with LLM code generation these days: I've been there, I've done that, I vaguely know what the right code would look like when I see it. Rather than spend 30-60 minutes refreshing myself to swap the context back into my head, I prompt Claude to generate a thing that I know can be done. Much of the time, it generates basically what I would have written, but faster. Sometimes, better, because it has no concept of boredom or impatience while it produces exhaustive tests or fixes style problems. I review, test, demand refinements, and tweak a few things myself. By the end, I have a working thing and I've gotten a refresher on things anyway. 5. As a customer, I don't want to pay for vibe-coded products, because authors also don't have a time (and/or skills) to properly review, debug and fix products. 6. The head chefs at most restaurants delegate the majority of details of dishes to their kitchen staff, then critique and refine. 7. Sure, as long as you don’t expect me to digest it, live with it, and crap it out for you, I see no problem with it. 8. There is no x is because LLM performance is non deterministic. You get slop out at varying degrees of quality and so your job shifts from writing to debugging. 9. Mmm, I do a lot of frontend work but I find writing the frontend code myself is faster. That seems to be mostly what everyone says it's good for. I find it useful for other stuff like writing mini scripts, figuring out arguments for command line tools, reviewing code, generating dumb boilerplate code, etc. Just not for actually writing code. 10. My problem is that code review has always been the least enjoyable part of the job. It’s pure drudgery, and is mentally taxing. Unless you’re vibe coding, you’re now doing a lot of code review. It’s almost all you’re doing outside of the high-level planning and guidance (which is enjoyable). I’ve settled on reviewing the security boundaries and areas that could affect data leaks / invalid access. And pretty much scanning everything else. From time to time, I find it doing dumb things- n+1 queries, mutation, global mutable variables, etc, but for the most part, it does well enough that I don’t need to be too thorough. However, I wouldn’t want to inherit these codebases without an AI agent to do the work. There are too many broken windows for human maintenance to be considered. 11. Worse, you’re doing code review of poorly written code with random failure modes no human would create, and an increasingly big ball of mud that is unmaintainable over time. It’s just the worst kind of reviewing imaginable. The AI makes an indecipherable mess, and you have to work out what the hell is going on. 12. > My problem is that code review has always been the least enjoyable part of the job. The article is about personal projects. The need to review the code is usually 10x less :-) 13. For most of my AI uses, I already have an implementation in mind. The prompt is small enough that most of the time, the agent would get it 90% there. In a way, it's basically an advanced autocomplete. I think this is quite nice cause it doesn't feel like code review. It's more of a: did it do it? Yes? Great. Somewhat? Good enough, i can work from there. And when it doesn't work, I just scrap that and re-prompt or implement it manually. But I do agree with what you say. When someone uses AI without making the code their own, it's a nightmare. I've had to review some PRs where I feel like I'm prompting AI rather than an engineer. I did wonder if they simply put my reviews directly to some agent... 14. Agreed. I've settled on writing the code myself and having AI do the first pass review. 15. I've tried vibe coding and hate it. I guess it's okay for people who are only interested in the result, but for me it takes all the fun out of programming. It doesn't feel like it has anything to do with programming at all. I will continue to "vibe code" out of necessity - saving time and achieving more than I can on my own. But I cannot possibly understand how someone could consider it fun. 16. AI has increased my productivity in dealing with side tasks in languages/frameworks I'm not familiar with. But it has not made development fun. To the contrary, I enjoy writing code, not reviewing code. 17. One thing is true: now I go to the bar with the other guys in the group, drink whatever and let Claude or Codex do the work while I supervise, then merge PR in the morning... I wish I was kidding, but for non critical projects this is now a reality 18. Web development may be fun again but you aren’t developing. You order and became a customer. Maybe you can distinguish good code from bad code but how long will you check it? Auditing wasn’t the fun part ever. And I bet at some point you will recognize a missing feeling of accomplishment because you didn’t figure out the how, you just ordered the what. We wouldn’t call someone a painter who let AI do the painting. 19. This is probably the best post i've seen about the whole LLM / vibe coding space at least in relation to web dev. Indeed, as the author states, the code / agent often needs some coralling, but if you know all the gotchyas / things to look for, you can focus 100% on the creativity part! Been loving it as well. 20. Except to me it feels more like AI is painting while I have to do the chores Write a concise, engaging paragraph (3-5 sentences) that captures the main ideas, notable perspectives, and overall sentiment of these comments regarding the topic. Focus on the most interesting and representative viewpoints. Do not use bullet points or lists - write flowing prose.
Code review burden with AI
20