201–210 of 675 posts
Earlier quoted context omitted.
> With enough rules and good prompting this is not true. There are atleast 10 posts on HN these days with the same discussion in circle. 1. AI sucks at code 2. you are not using my magic prompting technique
It's not magic. The techniques are well established and widely shared.
> 10x productivity means ten times the outcomes, not ten times the lines of code. This means what you used to ship in a quarter you now ship in a week and a half. Not really? That's defining productivity as latency, but it's at least as valid to define productivity as throughput. And then all the examples that are just about time spent waiting become irrelevant. When blocked waiting on something external, you just wo…
My point around waiting for things like code review is that it creates a natural time floor, the context switching takes time and slows down other work. If you have 10x as much stuff to get reviewed, all the time loss to context switching is multiplied by 10x.
> What LLMs produce is often broken, hallucinated, or below codebase standards. With enough rules and good prompting this is not true. The code I generate is usually better than what I'd do by hand. The reason the code is better all the extra polish and gold plating is essentially free. Everything I generate comes out commented great error handling, logging, SOLID, and united tested using established patterns in the…
Let’s talk about rules and docs, shall we? What makes a good rule for AI to keep it on task? What are your setups for docs and attaching them to the context (do you need to? Or just the location?) Let’s boil this down to an easy set of reproducible steps any engineer can take to wrangle some sense from their AI trip.
This was the best insight in the article: Do 10x engineers actually exist? "This debate isn't something I want to weigh in on but I might have to. My answer is sometimes, kinda. When I have had engineers who were 10x as valuable as others it was primarily due to their ability to prevent unnecessary work. Talking a PM down from a task that was never feasible. Getting another engineer to not build that unnecessary micr…
> Talking a PM down from a task that was never feasible One of our EMs did this this week. He did a lot of homework: spoke to quite a few experts and pretty soon realised this task was too hard for his team to ever accomplish, if it was even possible. Lobbied the PM and, a VP and a C-level, but managed to stop a lot of wasted work from being done. Sometimes the most important language to know as a dev is English* s/E…
What's your experience? And what do the "kids" use these days to indicate alternative options (as above — though for that, I use bash {} syntax too) or to signal "I changed my mind" or "let me fix that for you"?
I don’t think AI makes me 10x more productive. It does make me close to 10x less bored though. Much of production software engineering is writing boiler plate, building out test matrices and harnesses, scaffolding structure. And often, it’s for very similarly shaped problems at their core regardless of the company, organization, or product. AI lets me get a lot of that out of the way and focus on more interesting wor…
> Oh, and this exact argument works in reverse. If you feel good doing AI coding, just do it. If you feel so excited that you code more than ever before, that's awesome. I want everyone to feel that way, regardless of how they get there.
Not my experience.
You can instruct Claude Code to respect standards and practices of your codebase.
In fact I noticed that Claude Code has forced me to make few genuinely important things like documenting more, writing more E2E tests and tracking architectural and style changes.
Not only I am forcing myself to a consistent (and well thought styling), but I also need it later to feed it to the AI itself.
Seriously, I don't want to offend no one, but if you believe that AI doesn't make you more productive you've got skill issues in adopting and using new tools at what they are good at.
Earlier quoted context omitted.
Hi there! I appreciate your comment, and I remember reading your article about AI and some of the counterarguments to it helped me get over the imposter syndrome I was feeling. To be clear, I did not classify "all the AI-supporters" as being in those three categories, I specifically said the people posting that they are getting 10x improvements thanks to AI. Can you tell me about what you've done to no longer have an…
Can you help me understand which articles you're referring to? A link to the biggest "AI made me a 10x developer" article you've read would certainly clear this up.
That seemed to me be to be the author's point.
His article resonated with me. After 30 years of development and dealing with hype cycles, offshoring, no-code "platforms", endless framework churn (this next version will make everything better!), coder tribes ("if you don't do typescript, you're incompetent and should be fired"), endless bickering, improper tech adopting following the FANGs (your startup with 0 users needs kubernetes?) and a gazillion other annoyances we're all familiar with, this AI stuff might be the thing that makes me retire.
To be clear: it's not AI that I have a problem with. I'm actually deeply interested in it and actively researching it from a math's up approach.
I'm also a big believer in it, I've implemented it in a few different projects that have had remarkable efficiency gains for my users, things like automatically extracting values from a PDF to create a structured record. It is a wonderful way to eliminate a whole class of drudgery based tasks.
No, the thing that has me on the verge of throwing in the towel is the wholesale rush towards devaluing human expertise.
I'm not just talking about developers, I'm talking about healthcare providers, artists, lawyers, etc...
Highly skilled professionals that have, in some cases, spent their entire lives developing mastery of their craft. They demand a compensation rate commensurate to that value, and in response society gleefully says "meh, I think you can be replaced with this gizmo for a fraction of the cost."
It's an insult. It would be one thing if it were true - my objection could safely be dismissed as the grumbling of a buggy whip manufacturer, however this is objectively, measurably wrong.
Most of the energy of the people pushing the AI hype goes towards obscuring this. When objective reality is presented to them in irrefutable ways, the response is inevitably: "but the next version will!"
It won't. Not with the current approach. The stochastic parrot will never learn to think.
That doesn't mean it's not useful. It demonstrably is, it's an incredibly valuable tool for entire classes of problems, but using it as a cheap replacement for skilled professionals is madness.
What will the world be left with when we drive those professionals out?
Do you want an AI deciding your healthcare? Do you want a codebase that you've invested your life savings into written by an AI that can't think?
How will we innovate? Who will be able to do fundamental research and create new things? Why would you bother going into the profession at all? So we're left with AIs training on increasingly polluted data, and relying on them to push us forward. It's a farce.
I've been seriously considering hanging up my spurs and munching popcorn through the inevitable chaos that will come if we don't course correct.
I don't believe that literal typing of code is the limiting factor in development work. There is the research and planning and figuring out what it is even you need to develop in the first place. By the time you know what questions to even ask an LLM you are not saving much time in my opinion. On top of that you introduce the risk of LLM hallucination when you could have looked it up from a normal web search yourself…
Things like: build a settings system with org, user, and project level settings, and the UI to edit them.
A task like that doesn’t require a lot of thinking and planning, and is well within most developers’ abilities, but it can still take significant time. Maybe you need to create like 10 new files across backend and frontend, choose a couple libraries to help with different aspects, style components for the UI and spend some time getting the UX smooth, make some changes to the webpack config, and so on. None of it is difficult, per se, but it all takes time, and you can run into little problems along the way.
A task like that is like 10-20% planning, and 80-90% going through the motions to implement a lot of unoriginal functionality. In my experience, these kinds of tasks are very common, and the speedup LLMs can bring to them, when prompted well, is pretty dramatic.
Earlier quoted context omitted.
Something I have realized about Hacked News is that most of the comments on any given article are from people who are responding to the headline without actually clicking through and reading it! This is particularly true for headlines like this one which stand alone as statements.
Perhaps that's my fault for making the title almost clickbaity. My goal was to get people who felt anxious about AI turning them into dinosaurs not feel like they are missing some secret sauce, so hopefully the reach this is getting contributes that. Again, appreciate your thoughts, I have a huge amount of respect for your work. I hope you have a good one!
Earlier quoted context omitted.
To date, I've not been able to effectively use Copilot in any projects. The suggestions were always unusably bad. The /fix were always obviously and straight up false unless it was a super silly issue. Claude Code with Opus model on the other hand was mind-blowing to me and made me change my mind on almost everything wrt my opinion of LLMs for coding. You still need to grow the skill of how to build the context and f…
Thanks for this perspective, but I am a bit confused by some of your takes: you used "Claude Code with Opus model" in "the same toy project" with great success, which led you to conclude that this will "make a vast majority of all jobs redundant". Toy project viability does not connect with making people redundant in the process (ever, really) — at least not for me. Care to elaborate where do you draw the optimism fr…
I called it a toy project because I'm not earning money with it - hence it's a toy.
It does have medium complexity with roughly 100k loc though.
And I think I need to repeat myself, because you seem to read something into my comment that I didn't say: the building blocks exist doesn't mean that today's tooling is sufficient for this to play out, today.
I very explicitly set a time horizon of 5 yrs.