AiFilter
Spliit
AiFilter | Spliit | |
---|---|---|
2 | 7 | |
50 | 488 | |
- | 24.4% | |
5.9 | 9.2 | |
3 months ago | 3 days ago | |
JavaScript | TypeScript | |
- | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
AiFilter
-
Ask HN: What have you built with LLMs?
A Twitter filter to take back control of your social media feed from recommendation engines. Put in natural language instructions like "Only show tweets about machine learning, artificial intelligence, and large language models. Hide everything else" and it will filter out all the tweets that you tell it to.
Runs on a local LLM, because even using GPT3 costs would have added up quickly.
Currently requires CUDA and uses a 10.7B model but if anyone wants to try a smaller one and report results let me know on github and I can give some help.
https://github.com/thomasj02/AiFilter
-
Show HN: AI-Powered Twitter Filter
While exploring new applications for local LLMs, I built a Chrome extension that filters your Twitter feed based on natural language instructions.
For instance, you can instruct it to "Hide all tweets, except for tweets about machine learning (ML), artificial intelligence (AI) and large language models (LLMs)."
I've tested it and got good results with a 10B parameter model, but I suspect a high-quality small model like Phi-2 might work almost as well.
It's open source and available at https://github.com/thomasj02/AiFilter
Video demo: https://www.youtube.com/watch?v=CligVVTC5io
Spliit
-
Ask HN: What have you built with LLMs?
For my expense sharing app [1], I added receipt scanning in a few minutes and a few lines of code by using GPT 4 with Vision. I am aware that LLMs often are a solution looking for a problem, but there are some situations where a bit of magic is just great :)
It is a Next.js application, calling OpenAI’s API using a plain API route.
[1] https://spliit.app
-
TripSplit VS spliit2 - a user suggested alternative
2 projects | 15 Jan 2024
-
splitio VS spliit2 - a user suggested alternative
2 projects | 15 Jan 2024
- Show HN: Spliit – Free and Open Source Alternative to Splitwise
-
Show HN: Spliit v2 – Free and Open Source Alternative to Splitwise
I created the project a couple of years ago to learn Go, but I just rewrote it using a stack I am more comfortable with (Next.js). I also made it open source [1], to feel free to contribute ;)
[1] https://github.com/scastiel/spliit2
-
Spliit v2 – Open Source alternative to Splitwise
I totally rewrote it (migrating the existing data of course) with a technology I am more familiar with (Next.js, React, TailwindCSS, Prisma…), and made the new version open source! Feel free to contribute by creating an issue or even a pull-request if you want 😉.
What are some alternatives?
Language-games - Dead simple games made with word vectors.
CX_DB8 - a contextual, biasable, word-or-sentence-or-paragraph extractive summarizer powered by the latest in text embeddings (Bert, Universal Sentence Encoder, Flair)
data-analytics - Welcome to the Data-Analytics repository
grand-slams-dashboard - ATP / WTA Grand Slam Tennis Dashboard. View all time major leaders, filter by tournament, analyze player major final performance