101–110 of 304 posts
From the tools which were used to design and develop the models (programming languages, libraries) to the operating systems running them to the databases used for storing training data .. plus of course they were trained mostly on open source code.
If OSS didn't exist, it's highly unlikely that LLMs would have been built.
I think vibe coding would greatly struggle with large open source projects unless your planning was exceptional and your comments on optimal coding style was exceptional, however...... For those small open source tools that many of us use daily and find invaluable, I actually think vibe coding is ideal for that. It can make a functional version quickly and you can iterate and improve it, and feel no loss for making i…
There are three or four projects I've always wanted to do, but were frontloaded with a lot of complexity and drudgery. Maybe the best feature of vibe coding is that it makes the regret factor of poor early choices much lower. Its kind of magic to go "you know what, I was wrong, let's try this approach instead" and not having to spend huge amounts of time fixing things or rewriting 80% of the project. It's made it a l…
Setting out to implement a feature only to immediately get bogged down in details that I could probably get away with glossing over. LLMs short circuit that by just spitting something out immediately. Of course it's of questionable quality, but once you get something working you can always come back and improve it.
Earlier quoted context omitted.
I'm not saying that you shouldn't use AI. There was a submission to a blog post discussing applications of AI but it got killed for some reason. https://news.ycombinator.com/item?id=46750927 I remain convinced that if you use AI to write code then your product will sooner or later turn into a buggy mess. I think this will remain the case until they figure out how to make a proper memory system. Until then, we still h…
> I remain convinced that if you write code then your product will sooner or later turn into a buggy mess. FYFY
Earlier quoted context omitted.
You won't have to ignore this stuff for long. Pretty soon it'll be mandatory to keep up. I've been a senior engineer doing large scale active-active, five nines distributed systems that process billions of dollars of transactions daily. These are well thought out systems with 20+ folks on design document reviews. Not all of the work falls into that category, though. There's so much plumbing and maintenance and wiring…
> I've been so not now, then?
Small bespoke personalized on the spot apps are the future with LLMs. The future will absolutely not be "How things are today + LLMs" The paradigm now for software is "build a tool shed/garage/barn/warehouse full of as much capability for as many uses possible" but when LLMs can build you a custom(!) hammer or saw in a few minutes, why go to the shed?
> when LLMs can build you an custom(!) hammer or saw in a few minutes, why go to the shed? Because I thought I needed a hammer for nails (employee payroll) but then I realized I also need it to screw (sales), soldering (inventory management) and cleanup (taxes). Oh and don't forget that next month the density of iron can lower up to 50%.
Good points. It does feel like that happens quite often
I'm never quite sure what to think of papers that have a conclusion and then build a mathematical model to support it.
I have been trying to use Claude code to help improve my opensource Java NLP location library. However trying to get it to do anything other than optimise code or fix small issues it struggles. It struggles with high level abstract issues. For example I currently have an issue with ambiguity collisions e.g. Input: "California" Output: "California, Missouri" California is a state but also city in Missouri - https://gi…
> it struggles It does not struggle, you struggle. It is a tool you are using, and it is doing exactly what you're telling it to do. Tools take time to learn, and that's fine. Blaming the tools is counterproductive. If the code is well documented, at a high level and with inline comments, and if your instructions are clear, it'll figure it out. If it makes a mistake, it's up to you to figure out where the communicati…
Small bespoke personalized on the spot apps are the future with LLMs. The future will absolutely not be "How things are today + LLMs" The paradigm now for software is "build a tool shed/garage/barn/warehouse full of as much capability for as many uses possible" but when LLMs can build you a custom(!) hammer or saw in a few minutes, why go to the shed?
> When OSS is monetized only through direct user engagement, greater adoption of vibe coding lowers entry and sharing, reduces the availability and quality of OSS, and reduces welfare despite higher productivity. Sustaining OSS at its current scale under widespread vibe coding requires major changes in how maintainers are paid. I can't think of even a single example of OSS being monetized through direct user engageme…
Small bespoke personalized on the spot apps are the future with LLMs. The future will absolutely not be "How things are today + LLMs" The paradigm now for software is "build a tool shed/garage/barn/warehouse full of as much capability for as many uses possible" but when LLMs can build you a custom(!) hammer or saw in a few minutes, why go to the shed?