Hacker Search

Find out what readers of Hacker News think about any topic!

67 followers

Find out what readers of Hacker News think about any topic!

67 followers

Visit website

LLMs

•

Hacker Search leverages Hacker News' comments and submissions to answer your questions. It is particularly useful when you're interested in understanding HN readers' sentiment about a topic, or when looking for expert insights on technical topics.

Free Options

Launch tags:Developer Tools•Artificial Intelligence•Tech news

Launch Team / Built With

Render Sandboxes: a computer for every agentRun untrusted code safely. Idle sandboxes cost nothing

Promoted

Avec

Maker

📌

Hi Product Hunt! I'm Jonathan and I built Hacker Search (https://hackersearch.net), an LLM-powered version of Hacker News' Ask HN. Unlike Ask HN, Hacker Search doesn't solicit new contributions from HN readers. Instead, it leverages Hacker News' historical data to answer questions, and offers LLM-generated summaries of those. I've used it for questions like "Should I use Drizzle or Prisma?" or "What is a good screen capture that allows easy zooming effects on Mac?". 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. I've been using it continually while building it, and have found it particularly useful to find software libraries recommended by HN or get quick vibe checks on hot topics. Please try it out and let me know what you think of it! I have to limit the number of LLM summaries each person can get for free, as this is entirely self-funded. If you hit the limit, you can subscribe for more summaries generated by a better model ($8/month), or bring your own compute by running inference on Ollama on your machine!

Report

2yr ago

Product Hunt

This is a neat project. What's been the biggest surprise so far, @jnnnthnn? And what are people searching for most often?

Report

2yr ago

Avec

Maker

@rrhoover Thanks Ryan, glad you like it! The biggest surprise so far is that folks use it as much for personal lifestyle questions as they do for technical questions. Queries like "how to get out of a rut" and "is nano hydroxyapatite a good substitute for fluoride?" have gotten a ton of traffic (and frankly the answers are quite good). AI is definitely the most researched topic overall. My guess is that that is partly because it's very much the topic of the day, and partly because folks are trying to cut through the hype. I see a lot of queries trying to determine things like the best vector DB, which LLMs to use, and so on.

Report

2yr ago

Congratulations on the PH launch, Jonathan. This is exactly how they should be using AI. Pick the best resource and turn it into something useful. Not how they do it right now scraping the internet for garbage. I love it so much. You might wanna work on the UI though. Jolly good, Ash (:

Report

2yr ago