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

Great! I tried it out by simply adding a prefix to the URL. I'm looking forward to comparison articles like "Alternative to Tavily" and "Alternative to Jina AI"!


It's very valuable that Swift codes is open-sourced under the MIT!


I came across a0.dev the other day, and I think your focus on Flutter specifically is a nice differentiator. I'll try it!


Nice to hear. Thanks!


It's a great product overall! However, as others have mentioned, if it can't be open source and requires granting strong permissions, I'm concerned about the security implications.


Cool! As others have already commented, I'm curious about how well it can handle data access while considering the permissions of external services.


Our team was just exploring an approach to building an AI Agent Builder by making API calls via LLM, so this is very helpful. I'll give it a try!


Interesting! Reach out if you want to chat about it :)


I have the same issue. I'm curious to see how it's implemented, so I'll take a look at the source code.


That's an interesting attempt! I think it's a good approach for prototyping using Gistr (https://www.getgistr.com/) Are you the developer of Gistr?


Yeah I created Gistr recently. I've just been playing with different ways to use the summarizing tech. I found this way easier than having to install the chrome extension I made and setting up an account.


Indeed, allowing users to try it through a demo product, rather than having them install a Chrome extension, makes it more accessible. This is insightful from a product marketing perspective. Thank you!


That’s a really fascinating approach! The idea of encoding secret messages into seemingly ordinary text using arithmetic coding and an LLM-based probability model is both clever and innovative. It’s impressive how this method allows for covert communication in public spaces while remaining indistinguishable from typical AI-generated content.

At the same time, it raises interesting discussions about both the ethical and security implications of such technology. Looking forward to seeing how this project evolves!


Interesting experiment! This feels like it could really expand the potential applications of LLMs. Exciting to see how AI can assist in debugging with live runtime context!


Extremely LLM-like writing style, do you translate your comments through one or something?


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

Search: