521–530 of 1001 posts
Here are some of my first results (free PWA):
https://fretool.dev-zoo.net (Fretboard visualizer)
https://atoy.dev-zoo.net (real time audio slowdown and looper)
https://harptool.dev-zoo.net (Harmonica helper)
Feel free to give my repos a star on GitHub, thx
Inspired by a friend getting a random email and it sparking a memory for me: https://pageday.org , a global message lottery where each day a random message is drawn to be the homepage.
The idea is to be able to publish campaigns globally in any location/language and also get qualitative recommendations on what to improve. For example, if people have typos in their search terms, Rudy recommends to add it as a keyword so it can maximise the conversion.
I've been working non-stop on my game development tutorial website: https://raizensoft.com/tutorials/ Currently it mainly focuses on libGDX which is my most favorite framework. I prefer code-centric approach because that's how game development should be in my opinion. Most of the tutorials are just pure coding with algorithms explanations. My goal is to build one of the most resourceful website for libGDX because it'…
For over a decade, I’ve thought about how most people seem to resist the advice about money. And also how all advice is based on the same idea: seeing where your money went and making monthly plans based on that.
I think people feel that this is a poor match for how money works. So they improvise. And because we tend to not discuss money with others, they improvise on their own. What this typically looks like is checking their balance and trying to pace things.
I’ve been trying to design the app around that. Providing support to what seems like a natural, instinctive approach to managing money.
Standard system notification comes at about 10%, and most of the time, in my case at least, whenever I miss that, the result is "laptop shutdown amidst an ongoing video meeting" or something like that. (Basically, too late before I act)
Just so that I don't miss the reminders, the app will show an overlay window with some text, following my cursor, and a custom sound.
I built a version this weekend, and am current doing a dogfooding exercise.
So over the past few years, I have seen how contexts have been steadily growing in AI apps. And while the context lengths of LLMs have also been increasing, they are still effectively about 200k tokens. The performance drops off a cliff after that (you might have noticed it as well with long AI chats).
It is a simple API that prunes away irrelevant parts of a context for a given prompt, a.k.a. context-aware pruning. Integration is super simple: just an extra API call before the final LLM API call. You can get an API from the website.
I would love to chat if this is something that is relevant to you and if you have any feedback on what we are building!
Earlier quoted context omitted.
Can you talk a bit about the tech stack?
React + Vite + Tailwind on the frontend; Netlify Functions for backend with Stripe, Supabase, and email integrations; content via Markdown build script; deployed on Netlify; linted with ESLint; JavaScript-only codebase LLMs wrote 99% of the code.