Alternatives
Products that do what I mapped HN's favorite books with GPT-4o does
Hey HN! I love finding new books to read on here. I wanted to gather the most mentioned books and recreate the serendipity of physical browsing. I scraped 20k comments from HN threads related to reading, extracted the references and opinions using GPT-4o mini, and visualised their embeddings as a map. - OpenAI's embeddings were processed using UMAP and HDBSCAN. A direct 2D projection from the text embeddings didn't yield visually interesting results. Instead, HDBSCAN is first applied on a high-dimensional projection. Those clusters tend to correspond to different genres. The genre…
- 1
- 2
- 3GC
With all the "what can GPT do", I went to dabble with it to see if I could do something that plays to its strengths rather than just speculating about "would it be good at that?" https://gist.github.com/shagie/ff2f67b33bb517f6a297e2da66530cf4 The basis for the prompt is: Classify following titles into one or more of {US Politics}, {World Politics}, {Technology}, {Security}, {Current Events}, {Boasting}, {Curiosity}, {Unknown} The results from the front page as I type this: 34152137 Technology: Lite XL: A lightweight text editor written in C and Lua 34151880 Curiosity:…
2022
- 4
- 5IM
When I read papers, I have to jump between multiple tabs to find the dataset, code, videos, peer reviews, and so on. I tried to fix this with this project. It started as a project just for papers on arXiv, but after its initial success on Twitter (got like 1.9k views: the most I have gotten for a post), I have now expanded it to include other openly available papers from PubMed Central, bioRxiv, medRxiv, and eLife. These papers have been linked with their genes, proteins, diseases, drugs, clinical trials, 3D protein structures, code, and cited and similar papers. This project now has four…
Jul 2026 · tomesphere.com
- 6AV
I found myself jumping between ChatGPT, tabs, and docs, but never building real understanding. This is my attempt at fixing that — for researchers, curious readers, and lifelong learners. Would love your thoughts on the interface, and whether this would be useful in your own work or otherwise.
2025 · proread.ai
- 7I4
It's our new text-to-image model: a 9.3B single-stream diffusion transformer trained entirely from scratch. We focused heavily on controllability through structured JSON prompts, with strong text rendering, spatial awareness through bounding box guidance, and color palette control. It has the best text rendering of any open-weight model we've tested so far, and the NF4 quantized checkpoint runs on a single 24GB GPU. For more technical details and examples see our blog post: https://ideogram.ai/blog/ideogram-4.0/ We will be happy to answer any questions :)
Jun 2026 · github.com
- 8IB
Hey HN community, I built a tool that helps optimize your post for hitting the first page of Show HN. How it works: I used a Hugging Face dataset of all Hacker News posts from the past 3 years and trained a model that predicts how successful your post might be. There's still a lot of randomness on HN, so nothing is guaranteed, but the tool helps optimize your post for higher odds. A couple of interesting findings: - GitHub repo links work x3 better than regular domains - Open-source tools have a steady virality rate (13.9% - one of the highest) - "I built" outperforms "We built" - Using…
May 2026 · wannalaunch.com
- 9IP
To be specific, the content is generated by a GPT-2 based model. https://amzn.to/2TCc0v2 Let me know if you have any questions :-)
2020
- 10TN
I’ve been hacking on a project called Bookshelf (https://www.bookshelf.diy/). It lets you take an archive — say, your Substack export, a bunch of PDFs, or even saved HTML files — and turn that into a retrieval-backed GPT that your readers can query. The idea is: instead of scrolling archives, they just ask questions. Answers are pulled only from your original content, with citations. It’s aimed at writers and researchers who want their work to be more discoverable — but without spinning up vector infra or fiddling with RAG pipelines. For context: I’ve always gone back to Paul…
2025 · bookshelf.diy
- 11RA
Hey HN! I built ProRead to solve the problem of getting stalled by walls of text in books or losing the big picture while reading. Key features: • Start from a bird's-eye view, then zoom into any level of detail • Interactive knowledge maps show how concepts connect • Seamlessly navigate between chapter summaries and original text • Ask questions in context with AI assistance • High-quality text-to-speech for any book, any level of summary • Upload any EPUB and start reading immediately We have 9 curated classics (Wealth of Nations, Crime and Punishment, etc.) ready to explore, plus you can…
2025 · proread.ai
- 12VH
There are two parts for this project: 1) The LLM-powered pipeline to extract citations (books + authors) from books and resolve them using both Wikipedia and Goodreads with offline copies I have. The result is data associating Books/Authors to other Books/Authors with accurate bibliographical information spanning centuries. 2) A WebGPU + D3.js powered visualization tool written by Claude Code so I'm able to deal with all this data on the browser on a more or less comfortable experience for the viewer. I spent some months on a off with this project, and definitely the most…
Feb 2026 · thiagolira.github.io
- 13VR
Sometimes I want to make sure I read every comment in a Thread. Also comments that come in later. For example, when I posted my laptop comparison map I got a ton of great feedback: https://news.ycombinator.com/item?id=8405065 and I wanted to make sure I don't miss any of these. For this purpose, I made this visual representation: http://social.gnod.com/hn:8405065 I think you can grok what it shows. It simply templates all comments in a recursive way. Read items turn blue. You can mark interesting items and they turn green. I find it interesting to look at…
2014
- 14AM
Hey, HN community! I'm excited to share the fifth issue of our AI/ML Weekly Digest. This innovative newsletter uses the power of GPT-4 to analyse and curate the most relevant and exciting AI/ML stories from Hacker News. This week I also share with our subscribers a curated list of resources during my learning journey https://github.com/vlameiras/ai-ml-resources/ GPT-4 scours through the top stories on Hacker News to bring you a concise summary and sentiment analysis of the hottest AI/ML news each week. Subscribe & Stay Updated To get the complete…
2023 · hn-ai-newsletter.beehiiv.com
- 15PF
Introducing embeds.ai: an embedding playground to compare how embedding models work on a real world use case (retrieval augmented generation for Wikipedia articles + Elad Gil's High growth handbook) A few weeks ago, Shreyan and I were looking for an embedding model to use for RAG. We eventually came across the MTEB leaderboard, but we struggled to understand the benchmark scores. We wanted a tool to test various embedding models with example queries on real-world datasets. After unsuccessfully looking for such a “playground”, we decided to just build one ourselves! We embedded HuggingFace’s…
2023 · embeds.ai
- 16IL
I built a tool for academics and practitioners that turns literature reviews into interactive, visual experiences. Upload PDFs and HTML sources, and AI creates a knowledge map showing how everything connects. What it does: - Upload research papers (PDFs) and web sources (HTML) - AI generates interactive knowledge maps from your sources - Skim read at a high level or read per-source/section summaries - Expand/build further specific sections of the map that interest you - Read original sources in context - Ask questions about the research and get contextual answers I have curated…
2025 · proread.ai
- 17SH
Been feeling a bit left out in this fast paced world of ML/AI, so built my first ML project since college. The idea is to scrape the most recent HN article titles and use TF-IDF and cosine similarity as metrics to rank articles that you're interested in to filter out only relevant things. Hopefully a fun project for beginners to get inspiration to jump into this world.
2023 · github.com
- 18AH
2022 · danieljanus.pl
- 19G5
After years on HN, I've built SmartResearchAI to solve what PhDs struggle with: finding answers in their mountain of PDFs. Today we add free GPT-5 access to our AI assistant. Core Capability Upload your research files (PDF/DOCX) → ask questions → get answers with inline citations pinpointing exact sources. GPT-5 Powered Features 1. Document Retrieval Mode - "Find conflicting methodology claims in these 3 papers" → Answers with [Source 1, p.12], [Source 2, p.4] - Extracts data from tables/figures with source links 2. Smart Synthesis - "Summarize Author X's theory using only my…
2025 · smartresearch-ai.com
- 20SB
Hey HN! My brothers and I have worked on this for the last 2 weeks. We use OpenAI's `text-embedding-ada-002` model to embed queries and a vector database to search for similar verses / blocks of verses. We'd like to see what you think and appreciate any feedback!
2023 · siliconscripture.org
- 21HR
2020 · hnrecommended.com
- 22HN
I recently received access to develop and use ChatGPT plugins, and embarked on a project to build a Hacker News integration as a learning exercise. My goal was to enable retrieval of content from HN to answer questions and produce insights in conversations with ChatGPT. I documented my journey in this blog post, which will hopefully be helpful to other plugin developers or anyone looking to learn more about embeddings. You can try the experience even if you don't have plugin access on ChatGPT through the demo on hn.kix.in - it's a loose approximation but should give you a sense of what's…
2023 · kix.in
- 23UI
My name is Victor, I’m Head of Product at DoubleCloud, a platform that helps data pros build sub-second data analytical solutions and pipelines on open-source technologies like ClickHouse, Apache Kafka, ETL and Business Intelligence services. Hearing from our users, we know how daunting it is to gather insights and try to make sense of all the charts, graphs and metrics, especially when you have to explain it to your business stakeholders. That’s why we’ve just launched our new feature — GPT-4 integrated into our platform’s BI tool. We all know how good ChatGPT is at summarizing texts. But…
2023 · double.cloud
- 24IP
It it always bugged me when I read or share an article, the discussion lives separately from the article. I imagined being able to add Google-Docs or Notion style comments on any website. We save a snapshot of the website and allow adding discussions that live side-by-side and directly reference parts of the article. HN articles are automatically indexed in https://cooo.link/hackernews and you can add any website, PDFs on https://cooo.link/ Built with SvelteKit, SingleFile(for archiving page), Railway. Solo dev. Would love feedback if you found it interesting!…
Mar 2026 · cool-link-web-production.up.railway.app
Ranked by how close each launch is in meaning, then by votes. Refine with a description →