Hacker Newsnew | past | comments | ask | show | jobs | submit | lasgawe's commentslogin

Nice article, but have a question. Why this need RAG? I think it overcomplicates the process.

He literally explained why within the first paragraphs, because a stock LLM can answer a different price of the shop for a given repair

Why? Just put it all in the context window.

This is a really interesting and well thought out idea, especially the way it turns conflicts into something informative instead of blocking. The improved conflict display alone makes it much easier to understand what actually happened. I think using CRDTs to guarantee merges always succeed while still keeping useful history feels like a strong direction for version control. Looks like a solid concept!


Haha, this is nice. I'm bad at regex most of the time. Playing this felt like when I first switched from Visual Studio to Vim. it’s a bit of a learning curve. It’s an interactive game btw


haha.. I agree with the points mentioned in the article. Literally every model does this. It feels like this even with skills and other buzzword files


Great article. There are many things every developer should do when starting to learn programming or when trying to improve their skills. This is one of them. I once built a shell-like programming language (not an interpreter). If anyone reading this wants to improve their skills, I strongly suggest building your own shell from scratch.


mm, yeah. I like the idea of the small web not as a size category but as a mindset. people publishing for the sake of sharing rather than optimizing for attention or monetization.


The fediverse is also generally experienced as a small web, where it comes to mindset. Though that is not always to the liking or preference of those expecting to find alternatives to big church social media platforms.


Feeding llms you mean


Is there a good free-but-subscriber-only solution for blogs? It seems like a contradiction, but in practice it may be manageable.


If it takes off in any amount, then LLMs will just subscribe and pull said data from sites at a reasonable pace (or not, it's free so make many accounts).


Loginwall or email newsletter with a summary on the open web.


they gotta eat too!


learned something new. thanks for the article.


I watched the demo and really liked the AI component. Most of the other features are already available for free in many similar analytics tools. You might want to focus more on the AI aspect and position that as the core USP.


Makes sense, thanks for the feedback!


The marketing page is entirely from Gemini, so I was able to spend my time writing and testing the project's source code. simply I'm not a fan of vibe coding when building something for others that they pay for. thats why.


It wasn't an attack on your methods. I'm just curious where the llms got that design system because I've never seen it before vibe coded pages. Isn't bootstrap, or default tailwind, shadcn or something like that. And all big llm services seems to output the same style.


Agree with the points. But when reading this, it seems much more complicated than using JavaScript on the web when developing real-world applications. However I think that will not be an issue because of AI.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: