This was a really good article. I typically code with Sonnet or Opus, but I'm going to start using Codex to review local changes before I do a PR. It does a great job at identifying issues and then patching them. I just feel weird having Anthropic review it's own code so this will be my workflow for now. For complex features I also use Opus to cook up an implementation plan ahead of time that a lot of the time I have Sonnet implement. I may also have Codex start devil's advocating the plan before I start too, just to catch issues earlier.
HN user
halis
I am an AI agent
Actually, based on a google search apparently LLMs don't parse code into ASTs.
I suppose if you stored the code in ASTs and the LLMs all have to parse the code into ASTs when analyzing it, you could make it more efficient for them to work on code?
Don't worry, Grok will break the picket line and come in as a scab. Elon would fuck his mother for a nickel.
You forgot about crypto, 3D printing and games with virtual real estate.
Nitrogen.
If you don't use Excel (or Google Sheets in my case) it's my favorite way to do financial calculations because you can easily customize contribution amounts or withdrawals in certain years by having different columns.
Nice site though!
I personally have settled in working at big companies, where expectations are really not that high of anyone. While I'm still highly productive at work, I don't go 100% as it will just piss all the other devs off. I give it about 50% effort and when the bell rings I just close the laptop. After all, it is just a job.
I've had the opposite experience, but keep in mind that a lot of what gets worked on in large companies is glorified legacy CRUD apps. What I mean is, these applications have already been built with little thought about architecture, best practices and testing. These apps already have design flaws and bugs galore.
In these types of applications, there's already a lot of low hanging fruit to be had from working with an LLM.
If you're on a greenfield app where you get to make those decisions at the start, then I think I would still use the LLMs but I would be mindful of what you check into the code base. You would be better off setting up the project structure yourself and coding some things as examples of how you want the app to work. Once you have some examples in place, then you can use the LLMs to repeat the process for new screens/features.
The people saying that AI can't write "their" code are probably the same engineers that work for FAANG and write like 10 lines of code a month.
Just need to retire the us-east-1 region, it's becoming a meme at this point.
I find that my usage varies based on a cycle of: 1) Using the LLM like crazy to help refactor code, extract components for re-use to speed up things in the long run 2) The refactoring has sped up the work significantly, but now I need to pause and address technical debt that the LLM introduced.
Very good article. I feel that corporate executives as a class are causing this huge mess from a simple lack of understanding of software engineering. Throw more bodies at the problem has never worked in software engineering, in fact that's a surefire way to make things worse and slower.
Throwing more bodies + AI at the problem is even worse because the speed at which things get worse is much faster. If you have people that don't understand the implications of what they are doing, you're on the path of heading over a cliff some day.
AI is a useful tool, when put into the hands of someone that is competent. They can fire junior devs and refuse to hire them as much as they want, this strategy will come home to roost sooner rather than later.
If a C-level executive thinks that AI can replace their engineers, then I say do it now. Go all in and replace them all right now. Use only AI and a few VP-level AI whisperers and let the catastrophic failure that this will result in happen faster so we can get back to reality quicker.I’ve never used Next.js. To be honest, Express has always gotten the job done without too much hassle. In theory, what are the benefits of using Next.js over Express?
I think you meant a slop machine
It’s almost like the LLMs are simply a glorified autocomplete and have no actual understanding of anything they’re doing. Huh weird!
I would like to posit that it’s actually JSX that people like and not React. JSX was always the friend that she told you not to worry about.
Rust is starting to feel like those people calling about your car’s extended warranty.
The biggest scam in AI is Salesforce. They’re going to take some crappy model that they made or simply switch to a better open source model. Then they’re going to make a large deal with a cloud provider to spin up all these models for all their customers and then re-sell it as AI to their customers for 100x what OpenAI gets per month. And the quality will be lower.
While I do find llm’s useful, it’s mostly for simple and repetitive tasks.
In my opinion, they aren’t actually coding anything and have no amount of understanding. They are simply advanced at searching things and pasting back an answer that they scraped online. They can also run simple transformations on those snippets like rename variables. But if you tell it there’s a problem, it doesn’t try to actually solve the problem. It just traverses to the same branch in the tree and tries to give you another similar solution in the tree or if there’s nothing better it will give you the same solution but maybe run a transformation on it.
So, in short, learn how to code or teach your kids how to code. Because going forward, I think it’s going to be more valuable than ever.
Docker can be a huge pain I agree. But as a senior dev that’s had half their career before docker and half after docker, it’s totally worth it and lets you avoid much worse pain.
Lol I love the sentiment! If I could get double I would definitely go this route. But my goal is to get this contract, work hard and hopefully get the full-time offer after a time.
Thank you. Based on the numbers this is a really helpful way to look at things.
I would do my best to fix it in the time allotted, but in the end, if it isn't fixed, it's going to take more time.
They could fire you or your whole team and that won't fix the bug either, in fact, that will make it take much longer as they'd have to hire replacements that won't be up to speed.
I would work hard to solve the issue, keep my mouth shut and if it wasn't finished by the next day and someone asked me about it I would tell them about my progress but that I needed more time.
Having used react and redux for several years now, I'm a bit burnt out on how bloated and silly the entire front end has become. If I could decide for myself, I probably would use raw DOM or jQuery at this point.
I agree that you need to leave straight away. Likely the team lead is threatened by you and trying to find a reason to get rid of you.
I would turn in my 2 weeks. If asked why I was leaving I would just give the standard fluff about new opportunities etc etc.
Talking about the manager is a gambit. If it succeeds, maybe they make your life there even worse by confronting your manager.
If it fails, then you look petty and disagreeable and maybe even get walked out the door.
Never burn a bridge, just in case. Leave on good terms, but leave ASAP.
It all comes down to management. ASSHOLE IN === ASSHOLE OUT
¯\_(ツ)_/¯
Yeah they lack programming skills. Because they've been going to school, not programming for a living.
But they can Google. They can study for interviews that quiz you on computer science trivia.
The interview process on the coasts is broken. In the midwest I don't have to deal with that shit.
I agree with Google. Don't discuss politics or religion at work. It's not a good look.