Find out what readers of Hacker News think about any topic!
Hacker Search leverages Hacker News' historical data to answer questions.
It is particularly useful when you're interested in understanding HN readers' sentiment about a topic, or when looking for expert insights on topics of interest to HN readers.
Tips - How to use Hacker Search effectively
- Formulate your query as a question addressed to the HN readership (e.g. “What do you think about...”)
- Familiarize yourself with the product by trying one of the sample questions below.
- If the results are not sufficiently relevant, try making your question more precise by disambiguating it (e.g. “What do you think about clerk for authentication” instead of “What do you think about clerk”)
- We cover all comments from the past 3 years. If you're interested in older data, or want to browse submissions instead of comments, try our search feature out instead!
Or read one of these sample questions:
Thirsty for more? Try our semantic search for Hacker News submissions.
Terms & Privacy Policy | This site is not affiliated with or sponsored by Hacker News or Y Combinator
{
"by": "jnnnthnn",
"descendants": 73,
"id": 40238509,
"kids": [
40238986,
40239439,
40241070,
40239867,
40242516,
40241048,
40239040,
40239328,
40239298,
40270799,
40239416,
40241470,
40262545,
40240279,
40239894,
40238849,
40241477,
40242397,
40244152,
40238894,
40241151,
40242319,
40241638,
40244926,
40239752,
40252696
],
"score": 233,
"text": "Hi HN!<p>I'm Jonathan and I built Hacker Search (<a href=\"https://hackersearch.net\" rel=\"nofollow\">https://hackersearch.net</a>), a semantic search engine for Hacker News. Type a keyword or a description of what you're interested in, and you'll get top links from HN surfaced to you along with brief summaries.<p>Unlike HN's otherwise very valuable search feature, Hacker Search doesn't require you to get your keywords exactly right. That's achieved by leveraging OpenAI's latest embedding models alongside more traditional indexes extracted from the scraped and cleaned up contents of the links.<p>I think there are many more interesting things one could build atop the HN dataset in the age of LLMs (e.g. more explicitly searching for technical opinions, recommending stories to you based on your interests, and making the core search feature more useful). If any of those sound interesting to you, head over to <a href=\"https://hackersearch.net/signup\" rel=\"nofollow\">https://hackersearch.net/signup</a> to get notified when I launch them!<p>Note: at least one person has built something similar before (<a href=\"https://news.ycombinator.com/item?id=36391655\">https://news.ycombinator.com/item?id=36391655</a>). Funnily enough, I only found out about this through my own implementation, and I based on my testing, I think Hacker Search generally performs better when doing keyword/sentence searches (vs. whole document similarity lookup), thanks to the way the data is indexed.",
"time": 1714669260,
"title": "Show HN: Hacker Search – A semantic search engine for Hacker News",
"type": "story",
"url": "https://hackersearch.net"
}
{
"author": null,
"date": null,
"description": "Actually relevant search",
"image": "https://hackersearch.net/ask/opengraph-image.png?e22ac334f80e3df2",
"logo": null,
"publisher": null,
"title": "Hacker Search",
"url": "https://hackersearch.net"
}
{
"url": "https://hackersearch.net/",
"title": "Hacker Search",
"description": "Find out what readers of Hacker News think about any topic!Hacker Search leverages Hacker News' historical data to answer questions.It is particularly useful when you're interested in understanding HN...",
"links": [
"https://hackersearch.net/"
],
"image": "https://hackersearch.net/ask/twitter-image.png?e22ac334f80e3df2",
"content": "<div><p>Find out what readers of Hacker News think about any topic!</p><p>Hacker Search leverages Hacker News' historical data to answer questions.</p><p>It is particularly useful when you're interested in understanding HN readers' sentiment about a topic, or when looking for expert insights on topics of interest to HN readers.</p><details><summary><span>Tips</span> - How to use Hacker Search effectively</summary><ul><li>Formulate your query as a question addressed to the HN readership (e.g. “What do you think about...”)</li><li>Familiarize yourself with the product by trying one of the sample questions below.</li><li>If the results are not sufficiently relevant, try making your question more precise by disambiguating it (e.g. “What do you think about clerk for authentication” instead of “What do you think about clerk”)</li><li>We cover all comments from the past 3 years. If you're interested in older data, or want to browse submissions instead of comments, <a target=\"_blank\" href=\"https://hackersearch.net/search\">try our search feature out</a> instead!</li></ul></details><p>Or read one of these sample questions:</p><p>Thirsty for more? Try <a target=\"_blank\" href=\"https://hackersearch.net/search\">our semantic search for Hacker News submissions</a>.</p></div><p><a target=\"_blank\" href=\"https://hackersearch.net/legal\">Terms & Privacy Policy</a> | This site is not affiliated with or sponsored by Hacker News or Y Combinator</p>",
"author": "",
"favicon": "https://hackersearch.net/favicon.ico",
"source": "hackersearch.net",
"published": "",
"ttr": 36,
"type": ""
}