121–130 of 410 posts
Earlier quoted context omitted.
And? Go create more stuff. Come back and post here when you have built something that has commercial success. Show us all how it's done. Until then go away - more noise doesn't help.
I don't think there's anything I could tell you about the companies I've built that would dissuade you from your perspective that everyone is as intellectually lazy as your projection suggests.
Earlier quoted context omitted.
A hundred times more time is spent reading a given piece of code, than it took writing it, in the lifetime of that program. OK I made up the statistic, but the core idea is true, and it's something that is rarely considered in this debate. At least with code you wrote, you can probably recognize it later when you need to maintain it or just figure out what it does.
Most code is never read, to be honest.
Earlier quoted context omitted.
The people who build the models don't understand how to use the models. It's like asking people who design CPUs to build data-centers. I've interviewed with three tier one AI labs and _no-one_ I talked to had any idea where the business value of their models came in. Meanwhile Chinese labs are releasing open source models that do what you need. At this point I've build local agentic tools that are better than anythin…
> The people who build the models don't understand how to use the models. It's like asking people who design CPUs to build data-centers. This doesn't match the sentiment on hackernews and elsewhere that claude code is the superior agentic coding tool, as it's developed by one of the AI labs, instead of a developer tool company.
You don't see better ones from code tooling companies because the economics don't work out. No one is going to pay $1,000 for a two line change on a 500,000k line code base after waiting four hours.
LLMs today the equivalent of a 4bit ALU without memory being sold as a fully functional personal computer. And like ALUs today, you will need _thousands_ of LLMs to get anything useful done, also like ALUs in 1950 we're a long way off from a personal computer being possible.
Earlier quoted context omitted.
My method is that I work together with the LLM to figure out the step-by-step plan. I give an outline of what I want to do, and give some breadcrumbs for any relevant existing files that are related in some way, ask it to figure out context for my change and to write up a summary of the full scope of the change we're making, including an index of file paths to all relevant files with a very concise blurb about what e…
The problem is, by the time you’ve gone through the process of making a granular plan and all that, you’ve lost all productivity gains of using the agent. As an engineer, especially as you get more experience, you can kind of visualize the plan for a change very quickly and flesh out the next step while implementing the current step All you have really accomplished with the kind of process described is make the world…
I can say the right precise wording in my prompt to guide it to a good plan very quickly. As the other commenter mentioned, the entire above process only takes something like 30-120 minutes depending on scope, and then I can generate code in a few minutes that would take 2-6 weeks to write myself, working 8 hr days. Then, it takes something like 0.5-1.5 days to work out all the bugs and clean up the weird AI quirks and maybe have the LLM write some playwright tests or whatever testing framework you use for integration tests to verify it's own work.
So yes, it takes significant time to plan things well for good results, and yes the results are often sloppy in some parts and have weird quirks that no human engineer would make on purpose, but if you stick to working on prompt/context engineering and getting better and faster at the above process, the key unlock is not that it just does the same coding for you, with it generating the code instead. It's that you can work as a solo developer at the abstraction level of a small startup company. I can design and implement an enterprise grade SSO auth system over a weekend that integrates with Okta and passes security testing. I can take a library written in one language and fully re-implement it in another language in a matter of hours. I recently took the native libraries for Android and iOS for a fairly large, non-trivial SDK, and had Claude build me a React Native wrapper library with native modules that integrates both natives libraries and presents a clean, unified interface and typescript types to the react native layer. This took me about two days, plus one more for validation testing. I have never done this before. I have no idea how "Nitro Modules" works, or how to configure a react native library from scratch. But given the immense scaffolding abilities of LLMs, plus my debugging/hacking skills, I can get to a really confident place, really quickly and ship production code at work with this process, regularly.
So we’re supposed to start paying $1k-$1,5k on top of already crazy salaries just to maybe get a productivity boost on trivial to semi trivial issues? I know my boss would not be keen on that at least.
Preventing garbage just requires that you take into account the cognitive limits of the agent. For example ... 1) Don't ask for large / complex change. Ask for a plan but ask it to implement the plan in small steps and ask the model to test each step before starting the next. 2) For really complex steps, ask the model to write code to visualize the problem and solution. 3) If the model fails on a given step, ask it t…
Right now it's not easy prompting claude code (for example) to keep fixing until a test suite passes. It always does some fixed amount of work until it feels it's most of the way there and stops. So I have to babysit to keep telling it that yes I really mean for it to make the tests pass.
Preventing garbage just requires that you take into account the cognitive limits of the agent. For example ... 1) Don't ask for large / complex change. Ask for a plan but ask it to implement the plan in small steps and ask the model to test each step before starting the next. 2) For really complex steps, ask the model to write code to visualize the problem and solution. 3) If the model fails on a given step, ask it t…
Genuine question: What do you mean by " ask it to implement the plan in small steps"? One option is to write "Please implement this change in small steps?" more-or-less exactly Another option is to figure out the steps and then ask it "Please figure this out in small steps. The first step is to add code to the parser so that it handles the first new XML element I'm interested in, please do this by making the change X…
So I'll say something like "evaluate the URL fetcher library for best practices, security, performance, and test coverage. Write this up in a markdown file. Add a design for single flighting and retry policy. Break this down into steps so simple even the dumbest LLM won't get confused.
Then I clear the context window and spawn workers to do the implementation.
Guy said a whole lot of nothing. Said he's improved productivity, but also said AI falls short in all the common ways people have noticed. Also guarantee no one is building core functionality delegating to Claude Code.
https://www-cdn.anthropic.com/58284b19e702b49db9302d5b6f135a...
Preventing garbage just requires that you take into account the cognitive limits of the agent. For example ... 1) Don't ask for large / complex change. Ask for a plan but ask it to implement the plan in small steps and ask the model to test each step before starting the next. 2) For really complex steps, ask the model to write code to visualize the problem and solution. 3) If the model fails on a given step, ask it t…
I've been vibe coding a couple of personal projects. I've found that test-driven development fits very well with vibe coding, and it's just as you said break up the problem into small, testable chunks, get the AI to write unit tests first, and then implement the actual code