louisfialho

makes sense, could you elaborate on the complexity? would like to understand what makes it a hard problem, thx!

Good point, raises a very interesting question: if the big websites block agents, won't agents be extremely limited? Should big websites 'charge' agents?

I think this was the case even 6 months ago but now that we have reasoning models I'd expect models can understand a web page and the action to take next no?

I see so basically saying this problem is too hard for a small team but the big labs will figure it out?

Thanks for the answers. Even the unexpected patterns like pop-ups etc to me feel pretty structured - I would expect models to generalize and navigate any of them I could see more websites blocking agents in the future but it seems like we're so early that this is not a limiting factor yet

If someone is actively working on this and believes there is a path please reach out to me

Agreed 100% - I have to clearly communicate that profiles are public by default, and add an option to make spaces / resources private! I did not realize how important this was to users, as I was using it mainly for myself until now. Thank you for the feedback!

Thank you! Chaos looks really nice - would you like to set up a quick call to discuss our respective product approaches? If so feel free to reach out at [email protected] !

Sweet - simple and effective - thank you for sharing!

Thanks! I am a big believer that "simplicity is the ultimate sophistication" so your feedback is encouraging! Feel free to reach out at [email protected] if you have any suggestion!

Thx! I'd be curious to learn more about your workflow - feel free to reach out at [email protected]

Love Airr! Tried it but did not manage to make it part of my daily routine - the audio highlighting feature somehow did not feel natural to me. However, I was really impressed with all the transcripts they generate - I think those could be super useful for me, once I have finished a podcast and want to retain key insights. Feel free to reach out by email - I'd be curious to learn more about your workflow!

Thanks for sharing this! I'd be super curious to learn more about your workflow - feel free to reach out at [email protected]

Hi Wes - thanks for your feedback! Indeed PKM is still a big, unsolved problem. Too bad many of the solutions created only end up being side projects - I still believe there is room for an end-to-end integrated "Figma" of resources management. Sent you an email to share our thoughts! Cheers

Thank you for the feedback - using a Telegram Bot is a useful hack to let users share resources from mobile without having an iOS app. This adds a small friction for non-Telegram users but is a good way to test demand!

Thanks for sharing this! The bot is here mainly as an MVP to let users share resources easily from mobile. In the future, it should be replaced by an ios app with traditional mobile sharing. Shelf is mainly focused on online learning resources but I'd be super curious to discuss your approach. Feel free to reach out at [email protected]

Hi Dexter - agreed, annotation is only one pain point among many others. I'd be curious to discuss our respective approaches for tackling this problem - feel free to reach out at [email protected] !

Hey vyrians - thank you for the feedback. Traffic from HN took the SMS API down but it should be back up. I also sent a link via e-mail for you to try to connect again. Let me know if you need support at [email protected] ! Cheers

Hi @pratio - thank you for the great questions! 1) How does this work? Whenever you encounter an interesting resource, say a podcast, a blog post, a newsletter, or a video, you can save it to your Shelf - either by using Telegram Bot from mobile or the 'Add' button from desktop. Once the resource is added to your shelf, you can assign it to a space, say "Neuroscience", in order to keep your resources organized. Finally, you can add notes to a resource in order to retain key insights, and share those with others if needed. For the v1 I focused on the 3 main pain points I had - save, organize and annotate resources - so that's pretty much it! Let me know what features would you like to see next! 2) What's the privacy policy? Every shelf is public for now. I believe in "open-source" knowledge and "learning in public". Knowledge is better shared than kept. 3) Is there a pricing plan at some point? Some users might adhere to 2) but still want private spaces. In this case, they could have to pay a small tax, say $2.99 for privacy (similar to GitHub's business model). 4) What's the limit? No limit! The beauty of technology is that, unlike our brains, it offers almost unlimited storage. 5) Send data using a telegram bot to a service? What kind of data can be sent? You can send URLs to Shelf Bot - those will be added directly to your Shelf and formatted accordingly (e.g. a URL for a podcast will be rendered as a podcast resource in Shelf) 6) Is this an alternative to pocket? Pocket is an amazing tool but it is almost 15 years old and quite abandoned by Firefox. This is a shame. I believe every user of the internet needs a place to save, organize and annotate information. Pocket could be 10xed.

Hi Tom, thanks for the feedback! Since the v1 is desktop only, building a Telegram bot was a hack to help users share resources directly from mobile - if things go right we'll build an ios app to replace the Telegram Bot! As for podcast annotation, the third video on the LP shows how the desktop experience works - and the mobile experience is pretty similar. Did you have a different type of experience in mind for podcast annotation? Thx!

I am both excited and terrified by the vast amount of high quality learning resources available online. Indeed, while I've learned so much for free online, it has also been hard to manage the information I encounter. More precisely it takes important mental effort to save, organize and annotate all the podcasts, blog posts, newsletters, articles, videos and other resources that are interesting. I have built and used Shelf personally for 2 weeks now and I am impressed at how efficient it has been in helping me convert information into knowledge more efficiently: I now save almost every resource with a glimmer of interest for later, but then ruthlessly prioritize resources that truly seem important, and finally systematically take notes for the very best resources. Curious to know how you deal with information overload and hope Shelf can help!