What is HN thinking? Real-time sentiment and concept analysis
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
Hi HN,I made Ethos, an open-source tool to visualize the discourse on Hacker News. It extracts entities, tracks sentiment, and groups discussions by concept.Check it out: https://ethos.devrupt.ioThis was a "budget build" experiment. I managed to ship it for under $1 in infra costs. Originally I was using `qwen3-8b` for the LLM and `qwen3-embedding-8b` for the embedding, but I ran into some capacity issues with that model and decided to use `llama-3.1-8b-instruct` to stay within a similar budget while having higher throughput.What LLM or embedding would you have used within the same price range? It would need to be a model that supports structured output.How bad do you think it is that `llama-3.1` is being used and then a higher dimension embedding? I originally wanted to keep the LLM and embedding within the same family, but I'm not sure if there is munch point in that.Repo: https://github.com/devrupt-io/ethosI'm looking for feedback on which metrics (sentiment vs. concepts) you find most interesting! PRs welcome!
HN · launched Feb 12, 2026 · 37 upvotes (top 23%) · 0 views
Niche: sentiment analysis software · 32 launches, 0 in the last 7 days · Explore this niche →
Category and tags
- Horizontal
- Analytics & BI
- Prosumer
- AI feature
- Hobby / open-source project
Visit website ↗ Source listing ↗
More like this: all 32 launches in sentiment analysis software →
Could you build this?
Yes Fetching public Hacker News API data, processing text through an LLM or embedding model, and displaying cluster charts via a static web app can be built quickly with vibe coding.
Discussion
20 comments analyzed.
Concerns raised: Sentiment analysis is unsophisticated and sloppy, Entity tracking produces inaccurate sentiment results, Limited context window eating prompts and increasing costs, Information not properly sent to prompt for comment hierarchy, Green colors in sentiment visualization not distinct enough
Feature requests: Expand historical data back to 2007, Improve prompt engineering for sentiment analysis, Better concept naming and disambiguation guidance in JSON schema, More sophisticated multi-level comment hierarchy processing, Improve entity tracking accuracy for better sentiment attribution
Competitors
Other products that read as similar to this one : 132 launches clear the similarity bar, closest 8 shown.
Attention rank: #46 of 133 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 106 days after the earliest competitor.
- I built an interactive HN Simulator · hn · 2025-11-24 · 538 upvotes · similarity 0.54
- Was tired of drowning in HN comments, so I built an AI Chief of Staff · hn · 2026-01-26 · 5 upvotes · similarity 0.50
- HN Companion · hn · 2026-02-10 · 31 upvotes · similarity 0.46
- Selbstbild · hn · 2026-07-05 · 6 upvotes · similarity 0.45
- Hindsight Models and Inference API · ph · 2026-11-04 · 73 upvotes · similarity 0.45
- I asked HN about AI agentic setups, here are 750 of the comments mapped · hn · 2026-11-06 · 5 upvotes · similarity 0.44
- HN.watch · hn · 2026-09-28 · 221 upvotes · similarity 0.44
- I built a tool that helps predict HN front page success · hn · 2026-05-03 · 26 upvotes · similarity 0.44
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.