Hacker News: __alexander

New comment by __alexander in "OpenAI "rogue" agent activities found on Wikimedia projects"

__alexander — Mon, 05 Oct 2026 19:07:23 +0000

Hi, if anyone has any data/reports related to rogue agents can they share it? I have 8 mirrored on a GitHub but I’d love to explore more. Link to mirror.

https://github.com/alexander-hanel/rogue-agents-data

New comment by __alexander in "My weird new hobby: Wandering around Tokyo on Google Maps"

__alexander — Thu, 24 Sep 2026 21:30:09 +0000

Buy a plane ticket and go. I once walked 10 miles in Tokyo and never got bored.

New comment by __alexander in "Ask HN: What are you working on? (September 2026)"

__alexander — Tue, 15 Sep 2026 01:31:52 +0000

I have been exploring reverse engineering using LLMs and Ghidra. A particular interest is in trying to understand how complexity can affect the process. I’m still learning but it’s been a fun way to explore LLMs. Here are my results using opencode https://alexander-hanel.github.io/StressingLLMs/opencode.htm...

New comment by __alexander in "Show HN: Stuxnet – A reconstructed source code of the infamous cyber-weapon"

__alexander — Tue, 08 Sep 2026 12:29:25 +0000

It was very feasible. The exploit to propagate via usb was CVE-2010-2568. Odds are you can still find details on it.

New comment by __alexander in "I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes"

__alexander — Tue, 25 Aug 2026 12:55:48 +0000

A single model was loaded at a time and each model was given a 90 minute timeout. This is how I’m running it (actually an older version because they deleted the repo and replaced it)

https://github.com/MiaAI-Lab/DeepSeek-v4-Flash-One-DGX-Spark

New comment by __alexander in "I spent $266 and four AI models to own my tablet. GLM-5.3 finished it in a day"

__alexander — Sun, 23 Aug 2026 16:07:19 +0000

> Claude Max plan I already pay for, until its safeguards cut me off

I hate to say it but this is why security researchers are moving to Chinese models with no safeguards. I literally hit cyber safeguards in codex 5 minutes ago.

Abliteration Without the Weights

__alexander — Sun, 23 Aug 2026 14:06:27 +0000

Article URL: https://weightless.msuiche.com/

Comments URL: https://news.ycombinator.com/item?id=49408963

Points: 2

# Comments: 0

New comment by __alexander in "I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes"

__alexander — Sun, 23 Aug 2026 13:22:30 +0000

In my benchmark Deepseek-v4-flash did much better than Qwen 3.8 27B at reverse engineering.

https://alexander-hanel.github.io/StressingLLMs/

Show HN: Stressing LLMs – Complexity Benchmark

__alexander — Mon, 17 Aug 2026 13:39:07 +0000

Hi HN, this has been a learning project for exploring local large language models. I’ve been wondering how well LLMs handle increasing levels of complexity. Does anyone have recommendations for other resources or research on this topic?

Comments URL: https://news.ycombinator.com/item?id=49330655

Points: 2

# Comments: 0

New comment by __alexander in "Spaghettifying DRAM"

__alexander — Thu, 13 Aug 2026 19:16:50 +0000

So nice to see Christopher Domas posting code again.

New comment by __alexander in "Codex Resets"

__alexander — Sun, 19 Jul 2026 15:42:45 +0000

I just learned the hard way that codex removes resets once the weekly cycle starts.

New comment by __alexander in "Show HN: Decomp Academy – Learn to decompile GameCube games into matching C"

__alexander — Sun, 28 Jun 2026 11:53:01 +0000

Hi OP, I would be careful if you profit from this project in anyway. Nintendo is not a company that takes reverse engineering of their hardware or games lightly. You will probably hear from their lawyers next week :(

New comment by __alexander in "NOLA 'Nacular: One man's crusade to preserve New Orleans's vernacular signage"

__alexander — Fri, 19 Jun 2026 03:10:53 +0000

For anyone interested in this style of art, I’d recommend checking out Margaret Kilgallen’s work. She had similar ideas in San Francisco during the 90s.

New comment by __alexander in "Has AI already killed self-help nonfiction books?"

__alexander — Tue, 16 Jun 2026 19:57:26 +0000

Personally, I see the self-help industry dying because people are starting to realize that it’s just a network of individuals selling products, promoting each other’s products, and creating new avenues to sell more products. I refer to it as the “self-help mafia.” Tim Ferriss kind of created it.

New comment by __alexander in "Law Enforcement's "Warrior" Problem (2015)"

__alexander — Fri, 12 Jun 2026 18:53:18 +0000

https://youtu.be/Dz5VzLz67WA?is=pLpKbcgZ59sJP7Co

New comment by __alexander in "What if remote working, not AI, is to blame for weak junior hiring?"

__alexander — Mon, 01 Jun 2026 12:40:17 +0000

Brace yourself, hybrid and return to office propaganda are coming.

New comment by __alexander in "Mystery Microsoft bug leaker keeps the zero-days coming"

__alexander — Thu, 14 May 2026 02:20:08 +0000

So weird that GitHub requires a login to view their BlueHammer repo.

https://github.com/Nightmare-Eclipse/BlueHammer

New comment by __alexander in "Denuvo has been cracked in all single-player games it previously protected"

__alexander — Mon, 04 May 2026 03:56:28 +0000

Does anyone have a link to how the crack works? I would love to see something more technical.

New comment by __alexander in "Why did the chicken cross the road?"

__alexander — Wed, 25 Mar 2026 13:07:03 +0000

https://youtu.be/HrZ8HbhnXYM?si=bc9DdHa7b8UFvHkj

New comment by __alexander in "LLMs not = Security Products"

__alexander — Sun, 01 Mar 2026 16:43:56 +0000

“!=“ is not a valid input for titles on HN.