SHshalinshah·Sep 4, 2021Submission
Show HN: Generate flashcards from any site on the internet through NLP
9 points · Open discussionkanyesthaker
qgqa-flashcards
JavaScript2021–2021
kanyesthaker / qgqa-flashcards
qgqa-flashcards
Question Generation - Question Answering for Automatic Flashcards
2Distinct people
2Mentions
0Explicit recommenders
66GitHub stars
What to know before exploring
What it is
Question Generation - Question Answering for Automatic Flashcards
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by 6-hour interval2 dated mentions
Observed mentions: 2021-08-30 20:00:56 UTC to 2021-09-04 00:32:01 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Aug 30, 18:00 | 2021-08-30 18:00:00 UTC | 2021-08-31 00:00:00 UTC | 1 | 1 | 0 |
| Aug 31, 00:00 | 2021-08-31 00:00:00 UTC | 2021-08-31 06:00:00 UTC | 0 | 0 | 0 |
| Aug 31, 06:00 | 2021-08-31 06:00:00 UTC | 2021-08-31 12:00:00 UTC | 0 | 0 | 0 |
| Aug 31, 12:00 | 2021-08-31 12:00:00 UTC | 2021-08-31 18:00:00 UTC | 0 | 0 | 0 |
| Aug 31, 18:00 | 2021-08-31 18:00:00 UTC | 2021-09-01 00:00:00 UTC | 0 | 0 | 0 |
| Sep 1, 00:00 | 2021-09-01 00:00:00 UTC | 2021-09-01 06:00:00 UTC | 0 | 0 | 0 |
| Sep 1, 06:00 | 2021-09-01 06:00:00 UTC | 2021-09-01 12:00:00 UTC | 0 | 0 | 0 |
| Sep 1, 12:00 | 2021-09-01 12:00:00 UTC | 2021-09-01 18:00:00 UTC | 0 | 0 | 0 |
| Sep 1, 18:00 | 2021-09-01 18:00:00 UTC | 2021-09-02 00:00:00 UTC | 0 | 0 | 0 |
| Sep 2, 00:00 | 2021-09-02 00:00:00 UTC | 2021-09-02 06:00:00 UTC | 0 | 0 | 0 |
| Sep 2, 06:00 | 2021-09-02 06:00:00 UTC | 2021-09-02 12:00:00 UTC | 0 | 0 | 0 |
| Sep 2, 12:00 | 2021-09-02 12:00:00 UTC | 2021-09-02 18:00:00 UTC | 0 | 0 | 0 |
| Sep 2, 18:00 | 2021-09-02 18:00:00 UTC | 2021-09-03 00:00:00 UTC | 0 | 0 | 0 |
| Sep 3, 00:00 | 2021-09-03 00:00:00 UTC | 2021-09-03 06:00:00 UTC | 0 | 0 | 0 |
| Sep 3, 06:00 | 2021-09-03 06:00:00 UTC | 2021-09-03 12:00:00 UTC | 0 | 0 | 0 |
| Sep 3, 12:00 | 2021-09-03 12:00:00 UTC | 2021-09-03 18:00:00 UTC | 0 | 0 | 0 |
| Sep 3, 18:00 | 2021-09-03 18:00:00 UTC | 2021-09-04 00:00:00 UTC | 0 | 0 | 0 |
| Sep 4, 00:00 | 2021-09-04 00:00:00 UTC | 2021-09-04 06:00:00 UTC | 1 | 1 | 0 |
What Hacker News says
2 sourcesShow HN: NLP Flashcards for Most of the Internet
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 posteriori
We do this by (1) Parsing the DOM tree of an HTML page for <p> tags on the client, and segmenting these into preprocessed chunks (2) Performing inference on question-generation with a T5-base model pretrained on SQuAD (3) Extractive quest
Read the rest
ion-answering with the chunk & question we've generated with RoBERTa, also pretrained on SQuAD.
No GPT-3 here— where's the fun in an API call when you can do it yourself. Ferret is built as a React.JS app deployed as a chrome extension, with models hosted on AWS Sagemaker.
Finally, why could this be helpful?
Human memory is lossy. Psychologists have shown for forever that your memory can be modeled with a forgetting curve. If you don't attempt to retain knowledge, you'll likely lose it. But most of the content we read online (technical blog posts, documentation, course notes, articles) gets ingested and quickly forgotten. We're interested in low-friction approaches to helping people better remember this content , starting with fellow engineers who depend on their ability to remember key concepts to do the best job.
We've open-sourced the full repo and are actively responding to PRs + issues. [3]. You can read more about the technical + product challenges we faced if that interests you as well. [4]
We appreciate all feedback and suggestions!
[1]https://chrome.google.com/webstore/detail/ferret/mjnmolplinickaigofdpejfgfoehnlbh
[2] https://en.wikipedia.org/wiki/Bayesian_statistics
[3] https://github.com/kanyesthaker/qgqa-flashcards
[4] https://samgorman.notion.site/Ferret-c7508ec65df841859d1f84e518fcf21d