Ask HN: What are you working on? (October 2024)
751–760 of 1001 posts
Re: Ask HN: What are you working on? (October 2024)
#752This is an ongoing experiment that david927 has been helping with (thanks!). The two previous in the sequence were: Ask HN: What are you working on (September 2024)? - https://news.ycombinator.com/item?id=41690087 - Sept 2024 (1041 comments) Ask HN: What are you working on (August 2024)? - https://news.ycombinator.com/item?id=41342017 - Aug 2024 (1424 comments) One thing I'd like to hone in on is that these threads a…
Re: Ask HN: What are you working on? (October 2024)
#753I haven't merged those improvements on the community edition (yet) because of time constraints.
The next thing I will be working on is the GitHub Marketplace.
Re: Ask HN: What are you working on? (October 2024)
#754Re: Ask HN: What are you working on? (October 2024)
#755I’m building a way for developers to easily deploy open source applications (Postgres, redis, sentry, elastic search, etc), plus have a full heroku like workflow for their own applications, all within their kubernetes cluster, with what I hope is a super intuitive and friendly UI. I’ve ran a start up and saw how SaaS-ified and expensive web tooling is (heroku, datadog, redshift, fivetran, etc), but how difficult it w…
I can't find any pricing info on that page except "Get started for 1$$" and then it wants me to sign in. No thanks. I'd like to know what I'm getting into before signing up.
Re: Ask HN: What are you working on? (October 2024)
#756Working on an essay as to why coding interviews are harmful: http://dgt.is/coding-interviews
That said, take-home assignments were very helpful for junior candidates who didn't have much experience on their resume.
Re: Ask HN: What are you working on? (October 2024)
#757I'm trying to OCR a very large book: 45 volumes of ~500 pages each. The digitization has been done (not very good but not too bad either), but the pages have comments in the margin and lots of footnotes. Just doing plain OCR doesn't really work because the notes in the margin and the footnotes get mingled with the text, which results in gibberish. But, when sent to Google Vision API, each page results in a json file…
Re: Ask HN: What are you working on? (October 2024)
#758I've eschewed jobs and even a funded YC startup to work on this idea for years, ideating. Just following my passion and deep belief I'm making a more effective way to learn a language while also strengthening an emotional relationship!
Re: Ask HN: What are you working on? (October 2024)
#759I'm working on a solution to the age-old problem of tracking my food intake. Every app I have every tried from the many dozens on the market has not met my need of a low friction simple UI tool, so I've built it myself. I've built Journable, a simple & frictionless chat-based & photo-based calorie tracker. Just type in what you've eaten, in as much or as little detail as you can. Or type in what you did for exercise.…
Re: Ask HN: What are you working on? (October 2024)
#760I'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 recom…
This is fantastic, Aaron! I love it! 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 gu…
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!