Show HN: I made a website to semantically search ArXiv papers (Score: 151+ in 12 hours)
Link: https://readhacker.news/s/6k4zE
Comments: https://readhacker.news/c/6k4zE
As a grad student (and an ADHDer), I had trouble doing literature review systematically. To combat this, I made a website that finds similar papers using the meaning of the thing I am looking for.
I used MixedBread's [^1] embedding model to generate vectors from the abstracts. I store and search similar vectors using Milvus [^2] and finally use Gradio [^3] to serve the frontend. I update the vector database weekly by pulling the metadata dataset from Kaggle [^4].
To speed up the search process on my free oracle instance, I binarise the embeddings and use Hamming distance as a metric.
I would love your feedback on the site :)
Happy Holidays!
[1]: https://www.mixedbread.ai/docs/embeddings/mxbai-embed-large-...
[2]: https://milvus.io/
[3]: https://www.gradio.app/
[4]: https://www.kaggle.com/datasets/Cornell-University/arxiv
Show HN: FixBrowser – a lightweight web browser created from scratch (Score: 152+ in 11 hours)
Link: https://readhacker.news/s/6k4pT
Comments: https://readhacker.news/c/6k4pT
Hello, I'm working on a web browser that focuses on being truly lightweight and designed for privacy.
At some point I've realized that much of the complexity and resource requirements of web browsers comes from JavaScript. This is because every part needs to be dynamic and optimized for speed.
So a few years ago I've started to work on a web browser that intentionally doesn't implement JavaScript, instead it contains an updated set of scripts that fix and improve various websites.
I've been using this approach using a proxy server for a few years as my primary way of web browsing with good results. It uses a whitelist approach where no resources are loaded from different domains by default (the fix scripts can override it to load images from CDNs, etc.). This avoids any trackers by default.
You can find more details on the homepage of the project:
https://www.fixbrowser.org/
I'm currently running a fundraiser to get it really going. All the foundation blocks are there it just needs some more work. Any support is welcome.
Ruby 3.4.0 (Score: 150+ in 4 hours)
Link: https://readhacker.news/s/6k4Da
Comments: https://readhacker.news/c/6k4Da
Trying out QvQ – Qwen's new visual reasoning model (Score: 150+ in 10 hours)
Link: https://readhacker.news/s/6k3Uy
Comments: https://readhacker.news/c/6k3Uy
T * sin (t)' ≈ Ornamented Christmas Tree (2013) (Score: 150+ in 6 hours)
Link: https://readhacker.news/s/6k4gj
Comments: https://readhacker.news/c/6k4gj
I sensed anxiety and frustration at NeurIPS 24 (❄️ Score: 150+ in 2 days)
Link: https://readhacker.news/s/6jVq6
Comments: https://readhacker.news/c/6jVq6
macOS menu bar app that shows how full the ISS urine tank is in real time (🔥 Score: 162+ in 1 hour)
Link: https://readhacker.news/s/6k43Y
Comments: https://readhacker.news/c/6k43Y
More men are addicted to the 'crack cocaine' of the stock market (❄️ Score: 153+ in 4 days)
Link: https://readhacker.news/s/6jQbH
Comments: https://readhacker.news/c/6jQbH
Tokyo released point cloud data of the entire city for free (Score: 151+ in 7 hours)
Link: https://readhacker.news/s/6k2Eg
Comments: https://readhacker.news/c/6k2Eg
E.W.Dijkstra: Simplicity is a great virtue ... complexity sells better. (Score: 151+ in 1 day)
Link: https://readhacker.news/s/6jYk2
Comments: https://readhacker.news/c/6jYk2
Ask HN: Programmers who don't use autocomplete/LSP, how do you do it? (Score: 150+ in 1 day)
Link: https://readhacker.news/c/6jXUN
I am totally fascinated by programmers who don't use many of the IDE features I take for granted today: autocomplete, language servers, and recently copilot
So to the devs who don't use these tools, how do you do it? Do you just remember every type and field in a codebase? What does your flow look like?
One example is that I cannot live without the language server go-to-definition feature. What do you do if you need to look up the definition/implementation of some function which is in some other file?
Intel shareholders file case asking ex CEO, CFO to return 3 years of salary (Score: 150+ in 5 hours)
Link: https://readhacker.news/s/6k2tc
Comments: https://readhacker.news/c/6k2tc
38th Chaos Communication Congress (🔥 Score: 157+ in 3 hours)
Link: https://readhacker.news/s/6k2t5
Comments: https://readhacker.news/c/6k2t5
The number pi has an evil twin (Score: 155+ in 5 hours)
Link: https://readhacker.news/s/6k2aR
Comments: https://readhacker.news/c/6k2aR
Making AMD GPUs competitive for LLM inference (2023) (Score: 151+ in 6 hours)
Link: https://readhacker.news/s/6jZSc
Comments: https://readhacker.news/c/6jZSc
CRT Simulation in a GPU Shader, Looks Better Than Black Frame Insertion (Score: 151+ in 16 hours)
Link: https://readhacker.news/s/6k4hv
Comments: https://readhacker.news/c/6k4hv
This open problem taught me what topology is [video] (Score: 156+ in 7 hours)
Link: https://readhacker.news/s/6k4AT
Comments: https://readhacker.news/c/6k4AT
Why making friends as an adult is harder (Score: 150+ in 17 hours)
Link: https://readhacker.news/s/6k38E
Comments: https://readhacker.news/c/6k38E
Masks, Smoke, and Mirrors: The story of EgyptAir flight 804 (Score: 151+ in 12 hours)
Link: https://readhacker.news/s/6k3G9
Comments: https://readhacker.news/c/6k3G9
Merry Christmas Everyone (🔥 Score: 164+ in 1 hour)
Link: https://readhacker.news/c/6k4q3
What are some of your favorite memories from Christmas? Share them here :)
- Josh :)
Automating the search for artificial life with foundation models (Score: 150+ in 22 hours)
Link: https://readhacker.news/s/6k26E
Comments: https://readhacker.news/c/6k26E
Demystifying Debuggers, Part 2: The Anatomy of a Running Program (Score: 150+ in 19 hours)
Link: https://readhacker.news/s/6jZYq
Comments: https://readhacker.news/c/6jZYq
Four limitations of Rust's borrow checker (❄️ Score: 151+ in 2 days)
Link: https://readhacker.news/s/6jVGi
Comments: https://readhacker.news/c/6jVGi
Hoarder: Self-hostable bookmark-everything app (❄️ Score: 153+ in 2 days)
Link: https://readhacker.news/s/6jVL4
Comments: https://readhacker.news/c/6jVL4
Adversarial Policies Beat Superhuman Go AIs (Score: 152+ in 1 day)
Link: https://readhacker.news/s/6jYrH
Comments: https://readhacker.news/c/6jYrH
Litestack: All your data infrastructure, in one Ruby gem (Score: 150+ in 1 day)
Link: https://readhacker.news/s/6jXvn
Comments: https://readhacker.news/c/6jXvn
WSDA, USDA announce eradication of northern giant hornet from the United States (Score: 150+ in 1 day)
Link: https://readhacker.news/s/6jXKm
Comments: https://readhacker.news/c/6jXKm
Why are cancer guidelines stuck in PDFs? (Score: 150+ in 9 hours)
Link: https://readhacker.news/s/6jZP8
Comments: https://readhacker.news/c/6jZP8
Build a Low-Cost Drone Using ESP32 (Score: 152+ in 7 hours)
Link: https://readhacker.news/s/6jZSs
Comments: https://readhacker.news/c/6jZSs
Show HN: Llama 3.3 70B Sparse Autoencoders with API access (Score: 151+ in 11 hours)
Link: https://readhacker.news/s/6jZ22
Comments: https://readhacker.news/c/6jZ22