For my use case (https://www.grokvocab.com/), I get proper JSON output without much effort. I am using Langchain4J (https://github.com/langchain4j/langchain4j) which automatically maps the output JSON to my POJO. I just prompt the model to return the output as JSON.

I searched on Google to check if banks were open on a certain day. The AI response on top said they were closed because it was a second Saturday, but it was actually a Wednesday.

I've been working on GrokVocab (https://www.grokvocab.com), an app to improve vocabulary without flashcards or memorization.

Everyone knows reading is the best way to build vocabulary, but many avoid it and turn to flashcards or spaced repetition because long texts can feel overwhelming, and they often have to refer to a dictionary.

This app gives users short, engaging passages focused on comprehension. While reading, users guess word meanings from context and find out whether they got it right by answering a few questions below. I believe this will be helpful for people who haven’t had much success with popular vocabulary learning methods.

I shared it on HN earlier (https://news.ycombinator.com/item?id=44543063), but it didn’t get much attention. If you're interested in novel learning methods or vocabulary, I’d love your feedback.

P.S. Login is required since the app uses LLMs to generate interesting passages. You can register with any non-existent email if privacy is a concern.

Had the same thought sometime back about AI discovering theory of relativity with only the data before 1905. It would give a definite answer about whether any reasoning involved in the LLM output.

It gets funnier if you consider the meme that Elon Musk is an alien who is building rockets just to go back to his home planet. :)

Didn't work for me as well. Mainly pacing and writing style. Didn't finish the book.

I used Apex Charts recently with VueJS. Happy with the exhaustive configuration options available for each charts. It worked well for my use case.

Micronaut + VueJS + Bulma is my go to stack now. I like the minimalistic approach of Bulma. Was able to create a responsive single page app with minimal effort. Themes feature is a welcome addition.

I'm glad that you go with Micronaut (not Spring Boot).

Sounds great. How do you handle the licenses for the desktop app? Custom solution or is there a library for it?

It’s a custom solution, zero regrets building it. Gives me total control over how it’s done and didn’t take me that long to implement

Recently did something similar for a java project using AOP. Basically adding an annotation to each method and logging the parameters before the method call and return values after the method call. Whenever there is an exception, a mail will be sent with the stacktrace along with the entire request path(including method calls, parameters and return values). Extremely useful for debugging and to proactively fix the issues.

Curious how you do this performantly for any non-trivial codebase. Like, consider a class whose logging representation is the data it contains, which can be arbitrarily large. Generally this is not an issue because it’s only logged rarely and on designated paths where people actually care about this and it was expected to be used in that fashion. How would this work for a large object that you pass to a function repeatedly, or in a deeply nested stack trace?

The project I worked on has a non-trivial codebase. So far I haven't seen any performance issues though I was worried initially. The idea is to use it during development and beta testing and switch it off later once the application is stable enough. Might keep it on for some more time if there are no performance issues.