I'm working on inq - a real ink pen that writes on real paper while simultaneously digitizing everything you write. Specifically working on the software for our mobile and web apps.
Among other things, my team has implemented access-based sharing using web links, like Google Docs for real paper handwriting. And we've just launched Quin, our AI assistant for real paper handwriting. Super useful for getting help with math, language learning, looking up relevant facts, generating ideas, etc.
Oh that's quite a feature! I think a lot of people would love to customize their pen with different colors/types of ink that way, you should definitely add it somewhere in the description or to the FAQ
Anoto | Real ink pens that also digitize | Full-time | EU, UK, South America (100% REMOTE) | anoto.com
Anoto originally pioneered ink pens that also digitize everything you write or draw. As of very recently, we have a brand new management and tech team, new funding, and very ambitious plans for the future.
We are hiring a Lead Product Engineer to set the quality standard and the pace for the ongoing development of our just-launched React Native app, LivePen.
Anoto | Real ink pens that also digitize | Full-time | EU, UK, Eastern US (all 100% REMOTE) | anoto.com
Anoto originally pioneered ink pens that also digitize everything you write or draw. As of very recently, we have a brand new management and tech team, and ambitious new plans for the future. I'm happy to share more details directly with people who are interested.
We're hiring for the following roles:
- Firmware engineers
- R&D engineers (focusing on prototyping new hardware & software ideas)
I'm working on a unique discovery app / recommender for books, tv, movies, video games, songs, youtube channels, newsletters and podcasts - and more categories soon!
Since my last update here, I've added more detailed personalized descriptions of recommendations (hit Describe to request), including a rating out of 10 for how well the item meets your preferences.
I've also added the ability to replace individual recommendations (this was the most requested new feature!). If you update your preferences, your replacements will use your updated preferences - pretty nice for fine tuning your results!
I was surprised to learn that each recommendation for preferences costs nearly 1 cent. From what I can tell, you don’t seem to be caching preferences. For example, each "Let's Go!" click on a show like say "Succession" generates some variation in the preference recommendations. My hunch is that if we ask LLMs to "over recommend" preferences based on the content you’re using (my guess is a mix of MovieLens, IMDb, TMDB, and Wikipedia) and do so in an ordered fashion (preference1 is a solid, but preference7 is a so-so), you could cache these results and strategically display them. For instance, when users choose to "fix" certain categories and get new recommendations for others, these "over recommendations" could help create variations without additional LLM calls. This could be repeated like N times until new categories require further LLM calls.
I am not sure if this would work with the personalized descriptions of recommendations part. I kind of love how they’re tuned based on my selected preferences.
I am curious about the design of the whole system. Fun project! Thanks.
Thanks, I'm glad you like it! That makes me very happy!
You're correct, I'm not caching the results right now. I determined that caching whole queries would not make much difference in the aggregate, since the vast majority of queries are unique. (However I also just saw that OpenAI added their own caching layer with lower prices for cached results, which is nice!)
However - the new Replace function was my first step toward fetching recommendations one-at-a-time - I agree that potentially opens up interesting new possibilities for caching and other things as well!
I really like your idea and the clean, simple execution! I'm looking forward to using it more in the coming days.
I'm curious about the technical side of things—how did you build the app, and how do its inner workings function? Is it open source? If possible, could you share more technical details?
I'm working on a web app that helps you discover new things to read, watch, listen to and play.
You start with either an example or a brief description. Then, you'll get relevant preferences to select from. Your recommendations are based on the preferences you select. Every run is different.
I've added some new features along with support for blogs/newsletters and podcasts over the past month, and improved the recommendations generally.
I'm working on a web app that helps you discover books, movies, TV shows, video games, and songs that you'll like. The app makes it super easy to describe what you're looking for and then gives you a unique set of 10 suggestions on each run.
It's the first solo project I've done in many years and I'm having a great time learning. I've also been able to get some great recommendations for myself and it's fun to use!
However, I gave it "Jane Eyre" (a mid-19th century novel by Charlotte Bronte; it's a classic) with the expectation that it will return "Wuthering Heights" – another a classic novel written in mid-19th century by Emily Bronte (yes the authors are related) – among other things. People who like Jane Eyre tend to like Wuthering Heights, and vice versa.
But everything it returned were new works – published in the last 20 years – of stories that are set in the 19th century.
The only filters applied were:
"Preferred: Gothic romance novel, Victorian literature, Highly influential classic literature, Early 19th-century England ".
So, something seems amiss for now. Nevertheless, it's a very cool idea.
(Edited to fix my grammar; English is not my first language, so pardon me for any mistakes.)
This is happening because I intentionally added a strong bias for more recent books. I thought that's what most people would be looking for - at least for fiction - and I also assumed there were other good ways to discover older books (lists, collections etc).
You're absolutely right though, it should give you some Victorian lit given your preferences! I'll work on addressing this.
This is amazing, bookmarked and will try and use it to discover some new artists.
It seems to reverse the song/artist names occasionally. For example I've got a recommendation of 'Russian Circles' by Harper Lewis, but it should be 'Harper Lewis' by Russian Circles.
It is also telling me the song 'Ten Billion People' is by As I Watch You From Afar (who have a song called '7 Billion People all Alive at Once'), however it's from Explosions in the Sky.
How to find "Military science fiction series" that are "Complex and Strategic" and includes "Space battles and tactics", "Action-packed sequences", "Strategic dialogue", "Multiple book series expansions", "Futuristic space environment", "Spaceships and battle fleets"? Use yogurrt. Never found it so easy to narrow down my interests and find new books. Thanks!
Bookmarked. It actually does seem to work well for the items I have selected. I actually got some interesting hits I feel compelled to look up now ( nice call on adding purchase link -- unobtrusive way to monetize it ).
This works surprisingly well. Just shared it with my sci fi group.
Idea: make an email opt-in and then new releases based on old preferences. My use case is always to go to DVDs/netflix releases, filter for sci fi and then high IMDB.
The results of the categories look similar to what happens when prompting ChatGPT with "describe a list of {genres/moods/etc.} for <content>". Also the links are all for query pages on amazon/spotify/etc, which says LLM to me (rather than a database). This dynamic schema generation -> UI supported query builder seems like a really interesting direction. I'd love to see it for the web more generally and I bet Exa.ai+LLM of choice would be a pretty good place to start. If it's an LLM I'm curious about hallucination rates and excited for future web-level RAG in only returning real objects.
Also you can supply content which doesn't exist and it will automatically infer genre and such (another strong indication of LLM). I.e. you can imagine the aesthetics of the kind of content you might want by title and then use the UI to explore real recs related to that.
PS to the creator: I love the simplicity of the design and the execution is inspiring. Sent a dollar for my searches :-)
You are spot on :) - including about potential additional and broader use cases for this kind of UI. Hoping I can explore that more. Thanks for the tip about Exa.ai!
Also, I'm sincerely flattered that you like the design and execution. Thank you for that and for your contribution!
This is a huge gap we have these days. Everything out there is incentivized to suggest the most selling stuff rather than unique and interesting stuff.
Yeah, this is definitely an important aspect of the problem I'm hoping to solve. I've found that selecting interesting preferences yields some interesting, non-obvious results "out of the box" - but if you really want to go off the beaten path try selecting the "Little known" preference under Other (and make it Required).
Among other things, my team has implemented access-based sharing using web links, like Google Docs for real paper handwriting. And we've just launched Quin, our AI assistant for real paper handwriting. Super useful for getting help with math, language learning, looking up relevant facts, generating ideas, etc.
See https://inq.shop/pages/app