frontpage.
newsnewestaskshowjobs

Made with ♥ by @iamnishanth

Open Source @Github

fp.

SectorC: A C Compiler in 512 bytes

https://xorvoid.com/sectorc.html
84•valyala•4h ago•16 comments

Brookhaven Lab's RHIC concludes 25-year run with final collisions

https://www.hpcwire.com/off-the-wire/brookhaven-labs-rhic-concludes-25-year-run-with-final-collis...
23•gnufx•2h ago•14 comments

The F Word

http://muratbuffalo.blogspot.com/2026/02/friction.html
35•zdw•3d ago•4 comments

Software factories and the agentic moment

https://factory.strongdm.ai/
89•mellosouls•6h ago•167 comments

I write games in C (yes, C)

https://jonathanwhiting.com/writing/blog/games_in_c/
131•valyala•3h ago•99 comments

Speed up responses with fast mode

https://code.claude.com/docs/en/fast-mode
47•surprisetalk•3h ago•52 comments

Hoot: Scheme on WebAssembly

https://www.spritely.institute/hoot/
143•AlexeyBrin•9h ago•26 comments

Stories from 25 Years of Software Development

https://susam.net/twenty-five-years-of-computing.html
95•vinhnx•7h ago•13 comments

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

https://openciv3.org/
850•klaussilveira•23h ago•256 comments

First Proof

https://arxiv.org/abs/2602.05192
66•samasblack•6h ago•51 comments

The Waymo World Model

https://waymo.com/blog/2026/02/the-waymo-world-model-a-new-frontier-for-autonomous-driving-simula...
1091•xnx•1d ago•618 comments

Show HN: A luma dependent chroma compression algorithm (image compression)

https://www.bitsnbites.eu/a-spatial-domain-variable-block-size-luma-dependent-chroma-compression-...
4•mbitsnbites•3d ago•0 comments

Al Lowe on model trains, funny deaths and working with Disney

https://spillhistorie.no/2026/02/06/interview-with-sierra-veteran-al-lowe/
63•thelok•5h ago•9 comments

Vocal Guide – belt sing without killing yourself

https://jesperordrup.github.io/vocal-guide/
231•jesperordrup•14h ago•80 comments

Start all of your commands with a comma (2009)

https://rhodesmill.org/brandon/2009/commands-with-comma/
516•theblazehen•3d ago•191 comments

Reinforcement Learning from Human Feedback

https://rlhfbook.com/
93•onurkanbkrc•8h ago•5 comments

Selection Rather Than Prediction

https://voratiq.com/blog/selection-rather-than-prediction/
13•languid-photic•3d ago•4 comments

We mourn our craft

https://nolanlawson.com/2026/02/07/we-mourn-our-craft/
332•ColinWright•3h ago•397 comments

Coding agents have replaced every framework I used

https://blog.alaindichiappari.dev/p/software-engineering-is-back
254•alainrk•8h ago•412 comments

The AI boom is causing shortages everywhere else

https://www.washingtonpost.com/technology/2026/02/07/ai-spending-economy-shortages/
182•1vuio0pswjnm7•10h ago•251 comments

France's homegrown open source online office suite

https://github.com/suitenumerique
611•nar001•8h ago•269 comments

72M Points of Interest

https://tech.marksblogg.com/overture-places-pois.html
35•marklit•5d ago•6 comments

Show HN: I saw this cool navigation reveal, so I made a simple HTML+CSS version

https://github.com/Momciloo/fun-with-clip-path
27•momciloo•3h ago•5 comments

A Fresh Look at IBM 3270 Information Display System

https://www.rs-online.com/designspark/a-fresh-look-at-ibm-3270-information-display-system
47•rbanffy•4d ago•9 comments

Unseen Footage of Atari Battlezone Arcade Cabinet Production

https://arcadeblogger.com/2026/02/02/unseen-footage-of-atari-battlezone-cabinet-production/
124•videotopia•4d ago•39 comments

Where did all the starships go?

https://www.datawrapper.de/blog/science-fiction-decline
96•speckx•4d ago•107 comments

History and Timeline of the Proco Rat Pedal (2021)

https://web.archive.org/web/20211030011207/https://thejhsshow.com/articles/history-and-timeline-o...
20•brudgers•5d ago•5 comments

Learning from context is harder than we thought

https://hy.tencent.com/research/100025?langVersion=en
211•limoce•4d ago•117 comments

Show HN: Kappal – CLI to Run Docker Compose YML on Kubernetes for Local Dev

https://github.com/sandys/kappal
32•sandGorgon•2d ago•15 comments

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

https://github.com/valdanylchuk/breezydemo
287•isitcontent•1d ago•38 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."