Popular Posts

Popular Content

Powered by Blogger.

Search This Blog

Blog Archive

Follow on Google+

Recent Posts

About us

A year and a half after I published https://HackYourNews.com, I've rewritten it to be neater and added support for more news sources.

HackYourNews.com v1 had a great response on HN [1] and consistently sees ~2k weekly unique visitors.

There were many long-standing requests that I wanted to fulfill (thanks for your patience!): a proper dark mode, correct rendering on mobile devices, and more cogent summaries.

This rewrite is the result. gpt-4o-mini reduces the cost of summarization to an absurd degree, so it's now sustainable to keep this free service going!

Someday, I hope to use the Batch API [2] to drive down costs even further.

Enjoy.

[1] https://news.ycombinator.com/item?id=37427127

[2] https://help.openai.com/en/articles/9197833-batch-api-faq


Comments URL: https://news.ycombinator.com/item?id=43064166

Points: 6

# Comments: 0



from Hacker News: Front Page https://ift.tt/WAnZ6tb
Continue Reading

Hi HN, I’m Pablo, I built this application to learn languages using podcasts:

https://www.langturbo.com (No signup required)

There are a lot of tools to learn languages, but most of them focus on beginners (understandably so, that’s where the money is) but not many exist that target intermediate or advanced learners. The ones that exist make you find content on your own and then import that into their apps, which can be tricky when you don’t know where to look.

LangTurbo has a unique curated database of podcasts by language (some even have dialect labels) that you can browse by topic, or search by keyword, so you can discover content and learn in the same place.

Having a good language learning method is important, but having the motivation to keep learning is much more important. Some tools like Duolingo try to keep you motivated with “gamification”. I don’t like that, I think it gives you a false sense of accomplishment without real improvement. The way LangTurbo tries to keep you coming back is via the content itself. My goal is that you discover some podcast that interests you enough to keep coming back to listen to new episodes, the same way you listen to podcasts in your native language. I wrote more about the method here [1]

The app also lets you learn without looking at the screen, you can listen to a podcast in the background and for each sentence you will first hear the translation in English and the native speaker after. I call it “poor man's Pimsleur mode”.

Some things I learned while building the app:

* Currently the best SRS algorithm is FSRS, the app uses this algorithm implemented in SQL (thanks to [2])

* Working with Expo (React Native) was a great experience, the app has web, iOS and Android (coming soon) clients sharing most of the codebase.

* A lot of non-English podcasts have a feed with English as the language. I had to build a “probe” to get the correct language of a podcast, based on the text and audio of the feed.

* Podcasts use “Dynamic Ad Insertion”, that means the content of the audio can change according to the request IP or the time of the request.

* Still amazed by all the things Postgres can do

Let me know what you think, happy to answer any questions.

[1] https://www.langturbo.com/blog/langturbo/getting-started

[2] https://github.com/sivers/srs


Comments URL: https://news.ycombinator.com/item?id=43047554

Points: 17

# Comments: 14



from Hacker News: Front Page https://ift.tt/t2lbIGM
Continue Reading

Hi HN! Michael from Phind here.

We've spent the last 6 months rebuilding Phind completely. The new Phind goes beyond text to present answers visually with inline images, diagrams, cards, and other widgets to make answers more meaningful. We asked ourselves what types of answers we would like in an ideal world and crafted a new UI and model series to help get us there.

Phind is also now able to seek out information on its own. If it needs more information, it can do multiple rounds of additional searches to get you the most comprehensive answer it can.

This blog post contains an overview of what we did as well as technical deep dives into how we built the new frontend and models.

I'm super grateful for all of the feedback we've gotten from the HN community and can't wait to hear your thoughts!


Comments URL: https://news.ycombinator.com/item?id=43039308

Points: 5

# Comments: 0



from Hacker News: Front Page https://ift.tt/csIBhKR
Continue Reading