Alternatives
Products that do what NLP Flashcards for Most of the Internet does
Hello HN! We're Sam and Kanyes. We're building an extension to help you remember what you read online. We're calling it Ferret [1]. When you open Ferret on an HTML page, it generates recall-based questions + answers to reinforce key concepts with NLP. Consider the following toy example where we open Ferret on an explanation of Bayesian statistics. [2] Q: What does the frequentist interpretation view probability as? A: the limit of the relative frequency of an event after many trials Q: What is often computed in Bayesian statistics using mathematical optimization methods? A:The maximum a…
- 1
- 2MA
After 18 months of tinkering and iterating, we want to show you our Memex: An open-source browser extension to effortlessly organise your web-research. We'd love to know what you think :) Check it out at https://worldbrain.io/hn Memex features: - Instantly find websites you visited with the fuzzy memories you have about them, instead of bookmarking everything or keeping dozens of open tabs. Search for every word of every website you’ve seen, and filter by time, domain, custom tags or bookmarks. - Add your thoughts to websites via comments & annotations, directly in the browser…
2018
- 3
- 4CA
Hi HN — I'm the creator of FastMCP and wanted to share a new project we've open-sourced called Colin. I obviously love MCP, but I also use skills extremely heavily in my day-to-day work. Being exposed to both has made me very aware of a tension: - Anything with dynamic information, I ship over MCP. This takes work to set up and requires conversational boilerplate to refresh in every conversation. - Anything behavioral, I put in skills. They're lightweight, used automatically, and feel great. But I would never put dynamic information in a skill because keeping it up to date is a pain. And yet…
Jan 2026 · github.com
- 5RR
There's lots of improvements I'd like to make but thought I should get some feedback first to see if anyone's interested in it. The main page just shows the most recent feed items (currently from only the 3 feeds I've added myself), but the idea is that it'll show the most popular items aggregated from all users. It also provides TLDR summaries for each item, based on word frequency. http://bayfig.com EDIT: Typo
2010
- 6
- 7PG
Start a tweet with @letpgfinish, and it will be finished as if by Paul Graham himself. This was a weekend project I undertook with a couple of friends just for fun. The original one was @letkanyefinish, so you might like to try that out too... in fact, it seems to work much better (funnily enough, there's a definite inverse relationship between literacy of bot and literacy of its human counterpart). Anyway, the output is based on pg's essays and various tweets/quotes. Having used HN silently for a while, we thought we'd share this - so hope you enjoy :)
2014
- 8SN
Hi guys, I've been thinking a lot about how advancements in NLP can be standardized; when building a sentiment analysis, you know for sure that other attributes than the actual sentiment can be highly interesting, such as the urgency. Together with my team, I started a new open-source project, aiming to do exactly that. It's called bricks, and it is a composition of more than 50 open-source and modular code snippets, such as computing sentence complexities, emotionality detection and many more. For context, the idea came up after watching the incredible talk "Inventing on Principle" by Bret…
2022 · bricks.kern.ai
- 9AL
Hi there, I've been working on this library for a while. It started as having the need for just a few random generators that are statistically tested and it quickly escalated to 130+ distributions... So far that's the only library I've seen that has generators that are fully covered by tests. I hope you guys find it useful.
2022 · github.com
- 10VE
I'm building a Telegram bot to practice Dutch. GPT-4o-mini kept picking vocabulary words I already knew, so I built a classical NLP pipeline to do it instead. It takes a short text + learner level (A0–B1) and returns the best words to study, using Stanza for parsing and corpus frequency ranks (SUBTLEX-NL, srLex, SUBTLEX-US) for scoring. Wins at A1/A2, loses at A0 where the LLM picks more obvious words. I also tried adding multi-word phrases (ADJ+NOUN, VERB+NOUN, phrasal verbs) backed by NPMI-scored collocation whitelists. Couldn't beat GPT there because it just "knows" which phrases…
Mar 2026 · huggingface.co
- 11WA
Hi Hacker News, I'm excited to share a project I've been working on: a web-based word learning app designed to help you effortlessly expand your vocabulary. If you're learning a new language, especially German, this might be just what you need. What is it? This is a straightforward web application that leverages browser notifications to remind you of new words throughout the day. You upload a CSV file with your vocabulary list, and the app takes care of the rest. The notifications will pop up at intervals, displaying words and their translations to keep you engaged and learning. The CSV can…
2024 · word2go.netlify.app
- 12NO
2018 · nlpoverview.com
- 13OA
A friend and I are launching an alpha first thing in 2011. We're trying to gain some momentum and whatnot, so we're opening early registration as of tonight. We're planning to develop a Bayesian network to derive suggestions. If you're interested in seeing our progress, check it out. Edit: Any and all suggestions, criticism, advice, etc is highly appreciated!
2010 · osmoar.com
- 14GC
I've built an app that extracts interpretable 'circuits' from models using the GPT-2 architecture. These circuits reveal how specific inputs influence the probabilities of the next token in a sequence. While some tutorials present theoretical examples of how feedforward layers and attention heads may produce predictions, this app provides concrete examples of how information flows through an LLM. You can see, for example, the formation of features that search for simple grammatical patterns and trace their construction back to the use of more primitive features. Feel free to reach out with…
2024 · peterlai.github.io
- 15AA
An all-in-one blog for learning LLM ins and outs: tokenize, attention, PE, and more Project I've been diving deep into the internals of Large Language Models (LLMs) and started documenting my findings. My blog covers topics like: Tokenization techniques (e.g., BBPE) Attention mechanism (e.g. MHA, MQA, MLA) Positional encoding and extrapolation (e.g. RoPE, NTK-aware interpolation, YaRN) Architecture details of models like QWen, LLaMA Training methods including SFT and Reinforcement Learning If you're interested in the nuts and bolts of LLMs, feel free to check it out:…
2025 · comfyai.app
- 16PM
This is my attempt in building a memory that evolves and persist for claude code. My approach is inspired from Zettelkasten method, memories are atomic, connected and dynamic. Existing memories can evolve based on newer memories. In the background it uses LLM to handle linking and evolution. I have only used it with claude code so far, it works well with me but still early stage, so rough edges likely. I'm planning to extend it to other coding agents as I use several different agents during development. Looking for feedbacks!
Jan 2026 · github.com
- 17FE
Hey HN, We explored how decision-making happens under severe information asymmetry and used career exploration as a test subject. In practice, people converge on a small set of highly legible default paths, with little visibility into credible alternatives. That’s why we’re building Fig, a tool for reasoning about career paths when the next step isn’t obvious, given the dependence on fleeting personal preferences. Most existing tools respond by collapsing uncertainty into a single recommendation or by modeling careers as linear trajectories. That works reasonably well at the recruiting…
Jan 2026 · figcareer.com
- 18
- 19SR
Hi HN! Sipp is an open-source AI inference library for running local models in browsers with up to 3x faster decode speeds than alternative libraries. My background is in HCI (human-computer interaction) and graphics programming. Me along with my co-founder have been experimenting and thinking a lot about what the next user experience will look like when tokens are commodified to the point of being essentially “free.” A motivation for us was to try to move beyond the chat app and information retrieval use cases that are dominant now, and figure out how AI could instead act as a continuous…
Jun 2026 · sipp.sh
- 20GA
hi hn, today I'm open sourcing a new SQL-like query language that's built for the web. it has dedicated syntax for request, parsers, selectors, and javascript snippets... it was built on nodejs with the incredible moo lexer and nearley parser. if you're a fan of regular expressions, do I have some code to show you! the website is mostly just a few examples and a playground where you can write & run (& share!) your own queries. there's also an introductory blog post where i try but ultimately fail to justify why this should be its own language and not a library/framework. enjoy!
2024 · getlang.dev
- 21FT
After six months of work, I am here again presenting Fluent – a tiny lang which is optimized for differentiable & reactive programming. Since I am not Conal Elliot, don't expect a beautiful theoretical unification of FRP and AD from first principles. Rather, a horrific monster that holds together mostly because a lot of duct-tape. The link points to the semi-interactive tour of the language, which will get the job done much better than I could in here. Hope you hate/like it!
Jul 2026 · mlajtos.github.io
- 22EH
Hey HN, During my free time over 3 week summer vacation, I created a word game where you explain the word of the day to a language model using the most frequent 1,100 English words. I've been describing this to friends as "Wordle meets Thing Explainer". Hope you all enjoy it!
2024 · elevenhundred.games
- 23PG
I wanted to share a simple tool I just released: Tool: https://strongphrase.net/ Source: https://github.com/blanchardjeremy/strongphrase.net ## Background I have been researching password security and got interested in diceware passphrases (https://www.eff.org/dice). Though the original xkcd comic claims that it is somewhat easy to remember four or five words and turn them into a little scene, I often find it pretty hard to remember the diceware passphrases. (It's taken weeks for me to finally remember it). I found this tool…
2024 · strongphrase.net
- 24
Ranked by how close each launch is in meaning, then by votes. Refine with a description →