frontpage.
newsnewestaskshowjobs

Made with ♥ by @iamnishanth

Open Source @Github

fp.

If you lose your passport in Austria, head for McDonald's Golden Arches

https://www.cbsnews.com/news/us-embassy-mcdonalds-restaurants-austria-hotline-americans-consular-...
1•thunderbong•3m ago•0 comments

Show HN: Mermaid Formatter – CLI and library to auto-format Mermaid diagrams

https://github.com/chenyanchen/mermaid-formatter
1•astm•19m ago•0 comments

RFCs vs. READMEs: The Evolution of Protocols

https://h3manth.com/scribe/rfcs-vs-readmes/
2•init0•25m ago•1 comments

Kanchipuram Saris and Thinking Machines

https://altermag.com/articles/kanchipuram-saris-and-thinking-machines
1•trojanalert•25m ago•0 comments

Chinese chemical supplier causes global baby formula recall

https://www.reuters.com/business/healthcare-pharmaceuticals/nestle-widens-french-infant-formula-r...
1•fkdk•28m ago•0 comments

I've used AI to write 100% of my code for a year as an engineer

https://old.reddit.com/r/ClaudeCode/comments/1qxvobt/ive_used_ai_to_write_100_of_my_code_for_1_ye...
1•ukuina•30m ago•1 comments

Looking for 4 Autistic Co-Founders for AI Startup (Equity-Based)

1•au-ai-aisl•41m ago•1 comments

AI-native capabilities, a new API Catalog, and updated plans and pricing

https://blog.postman.com/new-capabilities-march-2026/
1•thunderbong•41m ago•0 comments

What changed in tech from 2010 to 2020?

https://www.tedsanders.com/what-changed-in-tech-from-2010-to-2020/
2•endorphine•46m ago•0 comments

From Human Ergonomics to Agent Ergonomics

https://wesmckinney.com/blog/agent-ergonomics/
1•Anon84•50m ago•0 comments

Advanced Inertial Reference Sphere

https://en.wikipedia.org/wiki/Advanced_Inertial_Reference_Sphere
1•cyanf•51m ago•0 comments

Toyota Developing a Console-Grade, Open-Source Game Engine with Flutter and Dart

https://www.phoronix.com/news/Fluorite-Toyota-Game-Engine
1•computer23•54m ago•0 comments

Typing for Love or Money: The Hidden Labor Behind Modern Literary Masterpieces

https://publicdomainreview.org/essay/typing-for-love-or-money/
1•prismatic•54m ago•0 comments

Show HN: A longitudinal health record built from fragmented medical data

https://myaether.live
1•takmak007•57m ago•0 comments

CoreWeave's $30B Bet on GPU Market Infrastructure

https://davefriedman.substack.com/p/coreweaves-30-billion-bet-on-gpu
1•gmays•1h ago•0 comments

Creating and Hosting a Static Website on Cloudflare for Free

https://benjaminsmallwood.com/blog/creating-and-hosting-a-static-website-on-cloudflare-for-free/
1•bensmallwood•1h ago•1 comments

"The Stanford scam proves America is becoming a nation of grifters"

https://www.thetimes.com/us/news-today/article/students-stanford-grifters-ivy-league-w2g5z768z
3•cwwc•1h ago•0 comments

Elon Musk on Space GPUs, AI, Optimus, and His Manufacturing Method

https://cheekypint.substack.com/p/elon-musk-on-space-gpus-ai-optimus
2•simonebrunozzi•1h ago•0 comments

X (Twitter) is back with a new X API Pay-Per-Use model

https://developer.x.com/
3•eeko_systems•1h ago•0 comments

Zlob.h 100% POSIX and glibc compatible globbing lib that is faste and better

https://github.com/dmtrKovalenko/zlob
3•neogoose•1h ago•1 comments

Show HN: Deterministic signal triangulation using a fixed .72% variance constant

https://github.com/mabrucker85-prog/Project_Lance_Core
2•mav5431•1h ago•1 comments

Scientists Discover Levitating Time Crystals You Can Hold, Defy Newton’s 3rd Law

https://phys.org/news/2026-02-scientists-levitating-crystals.html
3•sizzle•1h ago•0 comments

When Michelangelo Met Titian

https://www.wsj.com/arts-culture/books/michelangelo-titian-review-the-renaissances-odd-couple-e34...
1•keiferski•1h ago•0 comments

Solving NYT Pips with DLX

https://github.com/DonoG/NYTPips4Processing
1•impossiblecode•1h ago•1 comments

Baldur's Gate to be turned into TV series – without the game's developers

https://www.bbc.com/news/articles/c24g457y534o
3•vunderba•1h ago•0 comments

Interview with 'Just use a VPS' bro (OpenClaw version) [video]

https://www.youtube.com/watch?v=40SnEd1RWUU
2•dangtony98•1h ago•0 comments

EchoJEPA: Latent Predictive Foundation Model for Echocardiography

https://github.com/bowang-lab/EchoJEPA
1•euvin•1h ago•0 comments

Disablling Go Telemetry

https://go.dev/doc/telemetry
2•1vuio0pswjnm7•1h ago•0 comments

Effective Nihilism

https://www.effectivenihilism.org/
1•abetusk•1h ago•1 comments

The UK government didn't want you to see this report on ecosystem collapse

https://www.theguardian.com/commentisfree/2026/jan/27/uk-government-report-ecosystem-collapse-foi...
5•pabs3•2h ago•0 comments
Open in hackernews

Ask HN: Why can't Codex/Claude compile app and test that changes worked?

1•aurareturn•1w ago
Right now, both Codex and Claude makes changes based on your request but it's still you who needs to test those changes. Why can't Codex and Claude test them too?

For example, when making a change to the website, why can't Claude or Codex compile the changes, open a browser, test the changes to confirm that they worked?

It seems like the ability to verify is hugely important in autonomy. Yet, neither are doing it.

Comments

aurareturn•1w ago
It seems like Cursor can do this?
delaminator•1w ago
What do you mean?

Even Claude for Web can do the full compile edit cycle.

It runs Debian and apt installs stuff on demand and can run anything its Debian has.

I built a Chrome extension so Claude can get the full rendered DOM via a socket for web stuff.

Why do you think it can’t?

Are you perhaps using Claude Chatbot?

Claude Code will run anything you instruct it to.

I have to tell it to stop more than to start!

aurareturn•1w ago
So you had to build a Chrome extension for Claude so it can see its changes?

Can Claude Code open Chrome to test its changes by default?

No, not running chatbot. Running Claude Code CLI/Codex CLI.

delaminator•1w ago
I didn't have to no. It can run curl and get whatever HTML was served.

But how else would Claude see the live DOM ? The only way is through something running in the browser at runtime.

And yes, Google Chrome added an MCP into Chrome for doing it but I use Vivaldi.

When coding manually how would you check your code was working when it came to serving HTML?

Are you telling me your Claude / Codex cannot run curl to look at what was served?

If you need help with something you can ask, no need to be brusque.

aurareturn•1w ago
Why can't it just open the changes in Chrome and check it?
delaminator•1w ago
You mean like this?

    chrome --headless --dump-dom "https://example.com" > dom.html
aurareturn•4d ago
No. I don't need it to generate the html. I need it to render the service and check as well as clicking on the feature it built to test it.
delaminator•1w ago
I'm back at my desk now, here's something from my current Claude session of it writing and running code.

Are you saying yours cannot do this?

    Nawin.Auth is running on 567. Let me write a quick test to capture exactly what bytes Nawin.Auth sends vs Crabbit (on 5670):

    ● Write(/tmp/compare_auth.py)
       ⎿  Wrote 83 lines to ../../../../tmp/compare_auth.py
            1 #!/usr/bin/env python3
            2 """Compare auth server responses byte-by-byte"""
            3 import socket
            4
            5 def test_auth(host, port, name):
            6     print(f"\n=== Testing {name} on {host}:{port} ===")
            7
            8     # Build AuthTreq request (141 bytes)
            9     # type[1] + authid[28] + authdom[48] + chal[8] + hostid[28] + uid[28]
           10     request = bytearray(141)
          … +73 lines (ctrl+o to expand)

     ● Bash(sudo lsof -i :5670 2>/dev/null | head -3)
       ⎿  COMMAND     PID USER FD   TYPE DEVICE SIZE/OFF NODE NAME
          run-auth- 95646 root 9u  IPv4 139735      0t0  TCP \*:5670 (LISTEN)

     ● Bash(python3 /tmp/compare_auth.py 2>&1)
       ⎿ === Testing Nawin.Auth on 127.0.0.1:567 ===
         Request (141 bytes):
           Hex:              01676c656e6461000000000000000000000000000000000000000000006e6177696e00000000000000
         … +53 lines (ctrl+o to expand)

     ● Both send 145 bytes, same format! Differences are only in the random session keys (bytes 64-72 and 136-144). The ticket encryption is identical.
aurareturn•1w ago
It looks like it can execute scripts.

How about browser testing to verify?

theblazehen•1w ago
It can. For android, I have it dump screenshots and uiautomator xml dumps, and for web the playwright mcp.

I find that a critical step in agentic development is to close the loop for the LLM so it can get direct feedback without needing you to manually handle it.