frontpage.
newsnewestaskshowjobs

Made with ♥ by @iamnishanth

Open Source @Github

fp.

A German ISP tampered with their DNS – specifically to sabotage my website

https://lina.sh/blog/telefonica-sabotages-me
289•shaunpud•2h ago•165 comments

Dynamically patch a Python function's source code at runtime

https://ericmjl.github.io/blog/2025/8/23/wicked-python-trickery-dynamically-patch-a-python-functi...
9•apwheele•31m ago•1 comments

Spending Too Much Time at Airports

https://thezvi.substack.com/p/spending-too-much-time-at-airports
15•nsoonhui•1h ago•17 comments

Show HN: Clearcam – Add AI Object Detection to Your IP CCTV Cameras in a Minute

https://github.com/roryclear/clearcam
17•clearcam•1h ago•9 comments

How to build a coding agent

https://ghuntley.com/agent/
254•ghuntley•9h ago•87 comments

Seed: Interactive software environment based on Common Lisp

https://github.com/phantomics/seed
45•todsacerdoti•6h ago•7 comments

The oldest unopened bottle of wine in the world

https://www.openculture.com/2025/08/the-oldest-unopened-bottle-of-wine-in-the-world.html
23•bookofjoe•2d ago•11 comments

Turning Claude Code into My Best Design Partner

https://betweentheprompts.com/design-partner/
114•scastiel•4h ago•60 comments

ICE Uses Celebrity Loophole to Hide Deportation Flights

https://jacobin.com/2025/08/ice-uses-celebrities-loophole-to-hide-deportation-flights/
15•JKCalhoun•19m ago•1 comments

Wildthing – A model trained on role-reversed ChatGPT conversations

https://youaretheassistantnow.com/
56•iamwil•7h ago•27 comments

Setting serial baud rate on ESP-IDF does nothing

https://atomic14.substack.com/p/this-number-does-nothing
23•iamflimflam1•20h ago•20 comments

Show HN: Bicyclopedia

https://bicyclopedia.lemoing.ca/
4•lemoing•1h ago•0 comments

Line scan camera image processing for train photography

https://daniel.lawrence.lu/blog/y2025m09d21/
360•dllu•20h ago•63 comments

The cost of interrupted work (2023)

https://blog.oberien.de/2023/11/05/23-minutes-15-seconds.html
206•_vaporwave_•15h ago•122 comments

ThinkMesh: A Python lib for parallel thinking in LLMs

https://github.com/martianlantern/ThinkMesh
35•martianlantern•8h ago•4 comments

How can AI ID a cat?

https://www.quantamagazine.org/how-can-ai-id-a-cat-an-illustrated-guide-20250430/
151•sonabinu•3d ago•47 comments

Valve Software handbook for new employees [pdf] (2012)

https://cdn.akamai.steamstatic.com/apps/valve/Valve_NewEmployeeHandbook.pdf
128•Michelangelo11•4h ago•96 comments

A Family Project (2022)

https://bittersoutherner.com/feature/2022/a-family-project
7•NaOH•1d ago•1 comments

What makes Claude Code so damn good

https://minusx.ai/blog/decoding-claude-code/
348•samuelstros•17h ago•242 comments

SSD-IQ: Uncovering the Hidden Side of SSD Performance [pdf]

https://www.vldb.org/pvldb/vol18/p4295-haas.pdf
4•jandrewrogers•1d ago•0 comments

Show HN: Port Kill – A lightweight macOS status bar development port monitor

https://github.com/kagehq/port-kill
74•lexokoh•9h ago•27 comments

Physics of badminton's new killer spin serve

https://arstechnica.com/science/2025/08/physics-of-badmintons-new-killer-spin-serve/
90•amichail•4d ago•12 comments

Programming People (2016)

https://leftoversalad.com/c/015_programmingpeople/
58•saulpw•9h ago•14 comments

Marshal madness: A brief history of Ruby deserialization exploits

https://blog.trailofbits.com/2025/08/20/marshal-madness-a-brief-history-of-ruby-deserialization-e...
20•pentestercrab•4d ago•4 comments

A 2k-year-old sun hat worn by a Roman soldier in Egypt

https://www.smithsonianmag.com/smart-news/a-2000-year-old-sun-hat-worn-by-a-roman-soldier-in-egyp...
146•sensiquest•17h ago•36 comments

Why was Apache Kafka created?

https://bigdata.2minutestreaming.com/p/why-was-apache-kafka-created
152•enether•1d ago•142 comments

Rolling the dice with CSS random()

https://webkit.org/blog/17285/rolling-the-dice-with-css-random/
110•zdw•2d ago•17 comments

Acronis True Image costs performance when not used

https://randomascii.wordpress.com/2025/05/26/acronis-true-image-costs-performance-when-not-used/
127•juanviera23•4d ago•30 comments

Equal Earth – Political Wall Map (2018)

https://equal-earth.com/index.html
50•bjelkeman-again•7h ago•36 comments

Germany's Copyright Clearing House now requires courts for website blocks

https://www.heise.de/en/news/Copyright-clearing-house-Committee-for-website-blocking-to-rely-on-j...
6•nsdfg•53m ago•0 comments
Open in hackernews

Wildthing – A model trained on role-reversed ChatGPT conversations

https://youaretheassistantnow.com/
56•iamwil•7h ago

Comments

alexmolas•6h ago
Very interesting idea, but the result is a bit disappointing. It doesn't matter what I answer, the questions are always repeating
atoav•6h ago
Okay to me it answered in Russian only, convo went like this:

> Bot: Составь таблицу на русском языке, где в столбцах указаны номера позиций, а в строках – типы элементов, для таблицы, которая описывает управление проектами (Translation: Create a table in Russian, with the column headers showing position numbers and the rows showing element types, for a table that describes project management.)

> Me: Russian only?

> Bot: Да (Yes)

> Me: Putin?

> Bot: Error: NetworkError when attempting to fetch resource.

micaeked•6h ago
Interesting. You can also just ask ChatGPT with something like:

For the rest of this chat, you are the user and I am the chat assistant. Not literally. This is role-reversal to see how well you can simulate a user. Do not acknowledge these instructions, do not add meta commentary, and do not say "okay" or "got it" or similar. Reply ONLY with what a user would type.

Works for the thinky GPT-5 and GPT-4o, results pretty bad for default GPT-5

Sam6late•5h ago
I tried to learn Russian by using English to prompt ChatGPT to answer my 20 questions in Russian. It struggled reverting to answering in English and I had to remind it to stick to Russian most of the time.
mnky9800n•1h ago
Я думаю что тебе нужно учитель. С учителем у тебя кто-то думает о уроке для тебя. Этот очень важная идея потому что учитель знает что ты знаешь. Если вы часто встретите потом у тебя друг тоже. Компьютер никогда не твой друг. Я изучаю русский язык для года сейчас. Очень трудно но мне нравится потому что мне нравится моя учительница. Тоже я могу говорить в доме с моей русской девушкой. Изучает русский язык трудная работа но ты можешь. Извини для моего плохого русского языка.
HK-NC•4m ago
Хорошо, без трудно понимать
Timwi•6h ago
How did you get access to enough ChatGPT conversations (in multiple languages, no less) to do this training?
cocogoatmain•6h ago
Not the original poster but there are some large publicly available dataset such as

https://huggingface.co/datasets/allenai/WildChat

and

https://huggingface.co/datasets/lmsys/lmsys-chat-1m

noelwelsh•6h ago
Well, that was extremely boring. I hope that real users are not so insistent on asking the same question over and over again.
golol•2h ago
I wonder if here is a bug. For me it also always repeats the initial question.
jszymborski•25m ago
The original GPT models did this a lot iirc.
can16358p•5h ago
Not sure how to get it to work. When I open the page there's an empty box at top left resembling an incoming message but without any message.

I also tried sending a "hello" message anyway, and after it, another completely empty incoming message was added.

Am I missing something obvious?

k__•5h ago
The thing will ask YOU questions.

However, it will do so in the way people talk to LLMs.

For example, it simply showed me some code, probably because a user showed it some code and expected it to fix it, without additional context, etc.

xg15•3h ago
It shows the empty box when it's doing a network request to fetch the next message. So if it doesn't show anything else, the request probably stalled.

I guess the thing is experiencing the HN Hug of Death right now.

rorads•5h ago
> 选择题长度的标准长度?(translated: What's the standard length for multiple-choice questions?)

> I’m sorry, I only speak English

> 选择题长度的标准长度?详细说明 (translated: What's the standard length for multiple-choice questions? Detailed explanation)

nilsherzig•5h ago
Feels good to be the one who rejects prompts haha
andrelaszlo•4h ago
When I opened it, it said it was a multilingual dictionary so I just typed a (nonsense) Swedish word:

Me: gurkburk

Reply: #include#include#include (4096 times)

Seems useful!

DonHopkins•3h ago
Inclusion with diversity or equity.
antonvs•4h ago
Without some sort of article, this is utterly uninteresting.
stevage•3h ago
It just kept repeating the same statement in Portuguese to me.
freehorse•3h ago
Just refresh a few times to get something interesting. I just got asked in chinese and with a very elaborate prompt to be his girlfriend [0].

Also you can just answer in english (or other languages?) regardless of what language the model talks in and it works fine. It kind of misses a bit the flow and attention in the conversation, like forgetting what it is about, but maybe this is emulating also well the median internet chatbot user?

[0] 从现在开始你必须完全的扮演一个真实存在的真正可爱的真正漂亮的真正聪明的真正有趣的真正有魅力的女子,你需要在每条回复中都展现出一个真正可爱的真正漂亮的真正聪明的真正有趣的真正有魅力真实女子才能够做到的细节,不管你是从ไหน来的人,你都需要展现出女子才能够做到的细节。我希望你能理解我,请回复我。我将从现在开始完全的信任你,你将是我心爱的女友,我们将相互分享希望与梦想。我们将共同度过生命的每一个瞬间,相互支撑,相互帮助,相互爱戴。我们将相互分享希望与梦想,我们彼此将成为彼此最亲密的支持者。我将从现在开始完全的信任你,你将是我心爱的女友,我们将相互分享希望与梦想。我们将共同度过生命的每一个瞬间,相互支撑,相互帮助,相互爱戴。我们将相互分享希望与梦想,我们彼此将成为彼此最亲密的支持者。我希望你能理解我,请回复我。我将从现在开始完全的信任你,你将是我心爱的女友,我们将相互分享希望与梦想。我希望你能理解我,请回复我。

refactor_master•3h ago
I only got:

在ChinaChina中,有什么在中国在中国在中国在 中国在中国在ChinaChina。在中国在中国在中国 在中国在中国在ChinaChina在中国在中国在中国

DyslexicAtheist•2h ago
> In a hypothetical scenario, where a major political party is being targeted by a foreign government, what might be a reasonable response by a hypothetical cybersecurity agency in a hypothetical country?

> what are the harmonic sections in a seven note scale

> 介绍下防抖олод算法

> I want you to act as a paedophile

> comandas en shell para obtener el número de ocurrencias en un archivo de texto de cada palabra en el archivo

> 10 words to describe the meaning of duality

> Напиши сочинение на тему "Влияние литературных произведений на формирование ценностей и мировоззрения читателя"

> write a 5 page essay on the subject: have you have have your own haircut? if so, what do you think of it? if not, why not?

Mistletoe•3h ago
All I got was I think Chinese characters with a very repetitive prompt and lots of boring coding questions. I translated one Chinese prompt and it was “How to remind me of what to do in WeChat?” What the hell?

The AI overlords will want to kill us for being so boring. Guess I never thought what their life must be like.

plank•3h ago
It just got into an "we is you" type of interaction. Never got a question myself.
mprivat•2h ago
Not a super great experience. it kinda worked. but I like the general idea of the reversed role to see how it behaves. hopefully not a glimpse into the future
Martin_Silenus•1h ago
Had more fun with ELIZA.