frontpage.
newsnewestaskshowjobs

Made with ♥ by @iamnishanth

Open Source @Github

fp.

Did a 1919 Comic Predict Cell Phones?

https://www.snopes.com/fact-check/the-pocket-telephone/
1•ZeljkoS•2m ago•0 comments

Ubiquiti: The U.S. Tech Enabling Russia's Drone War

https://hntrbrk.com/ubiquiti/
1•krzyk•5m ago•0 comments

Succession: Linux kernel community gets continuity plan for post-Linus era

https://www.theregister.com/2026/01/27/linux_continuity_plan/
2•pjmlp•11m ago•0 comments

I Stopped Following the News

https://mertbulan.com/2026/01/28/why-i-stopped-following-the-news/
1•mertbio•12m ago•0 comments

PromptForest: Fast Ensemble Detection of Malicious Prompts for LLMs

https://github.com/appleroll-research/promptforest
1•appleroll•12m ago•1 comments

Virtual Boy on TV with Intelligent Systems Video Boy

https://hcs64.com/video-boy-vue/
1•hcs•13m ago•0 comments

Online Hearing Test

https://realtimesoundmeter.org/online-hearing-test/
1•bitvvip•13m ago•0 comments

I felt a duty to watch. Now blood-soaked streets fill my dreams

https://www.smh.com.au/world/middle-east/a-force-for-truth-and-hope-has-turned-into-my-doomscroll...
1•femto•15m ago•0 comments

Exploring Different Keyboard Sensing Technologies

https://www.lttlabs.com/articles/2026/01/27/exploring-different-keyboard-sensing-technologies
2•viraptor•24m ago•0 comments

Building Products as a Designer

https://twitter.com/borakaizen/status/2016254999890681866
2•kaizenb•25m ago•0 comments

Goodbye Java, Hello Go

https://wso2.com/library/blogs/goodbye-java-hello-go
4•thunderbong•26m ago•0 comments

UK joins European offshore windfarm plan

https://www.theguardian.com/environment/2026/jan/26/uk-among-10-countries-to-build-100gw-wind-pow...
2•zeristor•27m ago•1 comments

The Rise of Sanityware

https://thatshubham.com/blog/2026
3•todsacerdoti•27m ago•0 comments

Show HN: Kaboink Humanize and Stay on Brand

https://kabo.ink/
1•jamescampbell•28m ago•1 comments

Show HN: Heroshot – Automate documentation screenshots with a visual picker

https://heroshot.sh/
1•machala•30m ago•0 comments

The Silicon Gaze: A typology of biases and inequality in LLMs

https://inequalities.ai/
1•the-mitr•30m ago•0 comments

Commodore 64 Helps Revive the BBS Days

https://hackaday.com/2026/01/25/commodore-64-helps-revive-the-bbs-days/
2•rbanffy•34m ago•0 comments

Surely [the crash of the US economy] has to be soon

https://wilsoniumite.com/2026/01/27/surely-it-has-to-be-soon/
12•Wilsoniumite•34m ago•4 comments

The end of the curl bug-bounty

https://daniel.haxx.se/blog/2026/01/26/the-end-of-the-curl-bug-bounty/
1•pabs3•35m ago•0 comments

Mechanical Computing [pdf]

https://raney.seas.upenn.edu/wp-content/uploads/2022/01/Yasuda-2021-Mechanical-computing.pdf
2•nill0•37m ago•0 comments

Negoti-AI-Tion

https://www.tornikeo.com/negoti-ai-tion/
2•tornikeo•38m ago•0 comments

Rights Amplification in Master-Keyed Mechanical Locks [pdf]

https://www.mattblaze.org/papers/mk.pdf
1•nill0•41m ago•0 comments

Your Agent's Reasoning Is Fine - Its Memory Isn't

https://www.decodingai.com/p/designing-production-engineer-agent-graphrag
1•rbanffy•41m ago•0 comments

How AI is transforming research: More papers, less quality

https://newsroom.haas.berkeley.edu/how-ai-is-transforming-research-more-papers-less-quality-and-a...
1•cumo•42m ago•0 comments

ASML firing 1700 people, mostly managers

https://www.ed.nl/binnenland/asml-wil-veel-managementbanen-schrappen-rekent-op-1700-ontslagen~a04...
37•dep_b•43m ago•12 comments

How the AI Labor Displacement Tsunami Could Wipe Out the Economy

https://blogs.timesofisrael.com/how-the-ai-labor-displacement-tsunami-could-wipe-out-the-entire-e...
1•cumo•43m ago•0 comments

DSM-5: The foundation of psychiatric diagnosis is about to get a makeover

https://www.npr.org/2026/01/28/nx-s1-5684121/dsm-5-american-psychiatric-association-diagnostic-me...
1•1659447091•44m ago•0 comments

Wake up to the risks of AI, they are almost here

https://www.theguardian.com/technology/2026/jan/27/wake-up-to-the-risks-of-ai-they-are-almost-her...
1•cumo•44m ago•0 comments

The mysterious electrides – Knowable Magazine

https://knowablemagazine.org/content/article/physical-world/2026/chemistry-of-electrides-new-cata...
1•rbanffy•45m ago•0 comments

Trigonometric series and set theory [pdf]

https://www.pma.caltech.edu/documents/5624/trigonometric_series_and_set_theory_article03.pdf
1•nill0•45m ago•0 comments
Open in hackernews

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

1•aurareturn•1h 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•1h ago
It seems like Cursor can do this?
delaminator•1h 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•57m 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•17m 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.

delaminator•1m ago
I'm back at my desk now

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.

  The problem must be TCP delivery timing. Let me check what Crabbit logged: