frontpage.
newsnewestaskshowjobs

Made with ♥ by @iamnishanth

Open Source @Github

fp.

OpenCiv3: Open-source, cross-platform reimagining of Civilization III

https://openciv3.org/
624•klaussilveira•12h ago•182 comments

The Waymo World Model

https://waymo.com/blog/2026/02/the-waymo-world-model-a-new-frontier-for-autonomous-driving-simula...
926•xnx•18h ago•548 comments

What Is Ruliology?

https://writings.stephenwolfram.com/2026/01/what-is-ruliology/
32•helloplanets•4d ago•24 comments

How we made geo joins 400× faster with H3 indexes

https://floedb.ai/blog/how-we-made-geo-joins-400-faster-with-h3-indexes
109•matheusalmeida•1d ago•27 comments

Jeffrey Snover: "Welcome to the Room"

https://www.jsnover.com/blog/2026/02/01/welcome-to-the-room/
9•kaonwarb•3d ago•7 comments

Unseen Footage of Atari Battlezone Arcade Cabinet Production

https://arcadeblogger.com/2026/02/02/unseen-footage-of-atari-battlezone-cabinet-production/
40•videotopia•4d ago•1 comments

Show HN: Look Ma, No Linux: Shell, App Installer, Vi, Cc on ESP32-S3 / BreezyBox

https://github.com/valdanylchuk/breezydemo
219•isitcontent•13h ago•25 comments

Monty: A minimal, secure Python interpreter written in Rust for use by AI

https://github.com/pydantic/monty
210•dmpetrov•13h ago•103 comments

Show HN: I spent 4 years building a UI design tool with only the features I use

https://vecti.com
322•vecti•15h ago•143 comments

Sheldon Brown's Bicycle Technical Info

https://www.sheldonbrown.com/
369•ostacke•18h ago•94 comments

Microsoft open-sources LiteBox, a security-focused library OS

https://github.com/microsoft/litebox
358•aktau•19h ago•181 comments

Hackers (1995) Animated Experience

https://hackers-1995.vercel.app/
477•todsacerdoti•20h ago•232 comments

Show HN: If you lose your memory, how to regain access to your computer?

https://eljojo.github.io/rememory/
272•eljojo•15h ago•160 comments

An Update on Heroku

https://www.heroku.com/blog/an-update-on-heroku/
402•lstoll•19h ago•271 comments

Dark Alley Mathematics

https://blog.szczepan.org/blog/three-points/
85•quibono•4d ago•20 comments

Vocal Guide – belt sing without killing yourself

https://jesperordrup.github.io/vocal-guide/
14•jesperordrup•2h ago•6 comments

Delimited Continuations vs. Lwt for Threads

https://mirageos.org/blog/delimcc-vs-lwt
25•romes•4d ago•3 comments

Start all of your commands with a comma

https://rhodesmill.org/brandon/2009/commands-with-comma/
3•theblazehen•2d ago•0 comments

PC Floppy Copy Protection: Vault Prolok

https://martypc.blogspot.com/2024/09/pc-floppy-copy-protection-vault-prolok.html
56•kmm•5d ago•3 comments

Was Benoit Mandelbrot a hedgehog or a fox?

https://arxiv.org/abs/2602.01122
12•bikenaga•3d ago•2 comments

How to effectively write quality code with AI

https://heidenstedt.org/posts/2026/how-to-effectively-write-quality-code-with-ai/
244•i5heu•15h ago•188 comments

Introducing the Developer Knowledge API and MCP Server

https://developers.googleblog.com/introducing-the-developer-knowledge-api-and-mcp-server/
52•gfortaine•10h ago•21 comments

I spent 5 years in DevOps – Solutions engineering gave me what I was missing

https://infisical.com/blog/devops-to-solutions-engineering
140•vmatsiiako•17h ago•62 comments

Understanding Neural Network, Visually

https://visualrambling.space/neural-network/
280•surprisetalk•3d ago•37 comments

I now assume that all ads on Apple news are scams

https://kirkville.com/i-now-assume-that-all-ads-on-apple-news-are-scams/
1058•cdrnsf•22h ago•433 comments

Why I Joined OpenAI

https://www.brendangregg.com/blog/2026-02-07/why-i-joined-openai.html
132•SerCe•8h ago•117 comments

Show HN: R3forth, a ColorForth-inspired language with a tiny VM

https://github.com/phreda4/r3
70•phreda4•12h ago•14 comments

Female Asian Elephant Calf Born at the Smithsonian National Zoo

https://www.si.edu/newsdesk/releases/female-asian-elephant-calf-born-smithsonians-national-zoo-an...
28•gmays•7h ago•11 comments

Learning from context is harder than we thought

https://hy.tencent.com/research/100025?langVersion=en
176•limoce•3d ago•96 comments

FORTH? Really!?

https://rescrv.net/w/2026/02/06/associative
63•rescrv•20h ago•22 comments
Open in hackernews

Show HN: HN Sentiment API – I ranked tech CEOs by how much you hate them

https://docs.hnpulse.com
27•kingofsunnyvale•1mo ago
I built an API that extracts entities from Hacker News comments and classifies sentiment towards them as positive, negative, or neutral. It also classifies overall comment sentiment and assigns each entity a label (person, location, date, technology, organization, other).

505k+ comments, Oct 31 - Present.

Here's the leaderboard:

LOVED:

- Steve Jobs: 44% positive, 7% negative

- Linus Torvalds: 43% positive, 5% negative

- Gabe Newell: 34% positive, 8% negative

MID:

- Bill Gates: 22% positive, 8% negative

- Tim Cook: 15% positive, 30% negative

- Bezos: 12% positive, 18% negative

HATED:

- Zuckerberg: 4% positive, 35% negative

- Sam Altman: 8% positive, 38% negative

- Musk: 5% positive, 45% negative

Try it yourself:

# Who does HN talk about the most?

curl "https://api.hnpulse.com/entities?label=person&sort=mentions"

# What are people saying about remote work?

curl "https://api.hnpulse.com/comments?entity=remote work&limit=3"

# Is OpenAI's reputation getting worse?

curl "https://api.hnpulse.com/trends?entity=openai&bucket=day"

# What technology gets mentioned alongside SF?

curl "https://api.hnpulse.com/entities?co-occur=SF&label=technolog..."

Stack: Go, PostgreSQL, GPT-4o mini for entity extraction

Docs: https://docs.hnpulse.com API: https://api.hnpulse.com

Comments

dzrmb•1mo ago
Cool project! I'll definitely give it a go. Btw, did you use Elysia by any chance?
kingofsunnyvale•1mo ago
Thanks! I used Go + Chi, with Scalar for the docs. Elysia looks cool though - will look into it.
smt88•1mo ago
You're losing a lot from the binary here. Tim Cook isn't loved, sure, but it's rare to see someone rant about him the way they might about Bezos or Gates('s era of Microsoft)
verdverm•1mo ago
Very neat, I want to do something similar with my own comments, to see how I interact online and get the Ai to nudge me to better communications

Do you have a ballpark figure for how many tokens or dollars the analysis took?

kingofsunnyvale•1mo ago
It took 663,164,426 tokens and $238.21.
verdverm•1mo ago
that's... not terrible, thanks for sharing

I'd certainly be willing to spend a few hundred dollars organizing and annotating my collection of HN upvotes, chrome bookmarks, and social posts

gigatexal•1mo ago
What? DHH needs to be up there with Elon. SMH.
rsynnott•1mo ago
Kind of surprised about Bezos, though I suppose he lacks the extreme publicity seeking tendencies of the most-disliked.
kingofsunnyvale•1mo ago
Lately, I've been playing around with giving the API to claude-code to perform a sort of automated analysis of HN; this is what it says:

Analysis: Why Bezos Has Less Negative Sentiment

  The Numbers

  | Person     | Negative Sentiment | Total Mentions |
  |------------|--------------------|----------------|
  | Bezos      | 18-26%             | ~169           |
  | Zuckerberg | 35%                | ~201           |
  | Sam Altman | 38-43%             | ~501           |
  | Musk       | 39-45%             | ~1,119         |

  Bezos has roughly half the negative sentiment of the others AND is discussed 6-7x less than Musk.

  Your Hypothesis is Correct—But There's More

  1. Bezos is largely "retired" from controversy

  He stepped down as Amazon CEO in 2021. When he's mentioned on HN, it's mostly:
  - As a reference point for billionaire wealth alongside others ("Bezos/Musk/Ellison-type...")
  - Historical Amazon criticism ("Legacy of Bezos", "Day Two")
  - Generic billionaire tax discussions

  2. The others are making active, controversial decisions RIGHT NOW

  The co-occurrence data reveals what each person is discussed alongside:

  | Person     | Top Co-occurring Topics                           |
  |------------|---------------------------------------------------|
  | Musk       | Trump (61), Tesla, Twitter, DOGE (22), SpaceX     |
  | Altman     | OpenAI, ChatGPT, AGI, AI hype                     |
  | Zuckerberg | Facebook, Meta, Trump, censorship                 |
  | Bezos      | Amazon, Gates, other billionaires (as comparison) |

  3. Current actions generate current anger

  Looking at the negative comments:
  - Musk: "conman and liar", DOGE failures, political interference
  - Altman: "Scam Altman", AI resource hoarding, nonprofit betrayal
  - Zuckerberg: Censorship decisions, "kissing Trump admin's ring", Meta's social harm
  - Bezos: Mostly legacy Amazon issues or generic wealth criticism

  Conclusion

  It's not just that Bezos "seeks publicity less"—it's that he's not actively making decisions that affect the HN community. The others are:

  - Musk: Running Twitter/X (where many HN users are), advising Trump on government cuts
  - Altman: At the center of AI development that directly impacts tech workers
  - Zuckerberg: Making platform moderation decisions affecting global speech

  Bezos owns a newspaper and a space company but isn't making daily choices that intersect with tech workers' lives. He's transitioned from "active villain" to "historical reference."