frontpage.
newsnewestaskshowjobs

Made with ♥ by @iamnishanth

Open Source @Github

fp.

Start all of your commands with a comma (2009)

https://rhodesmill.org/brandon/2009/commands-with-comma/
256•theblazehen•2d ago•85 comments

Hoot: Scheme on WebAssembly

https://www.spritely.institute/hoot/
26•AlexeyBrin•1h ago•2 comments

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

https://openciv3.org/
706•klaussilveira•15h ago•206 comments

The Waymo World Model

https://waymo.com/blog/2026/02/the-waymo-world-model-a-new-frontier-for-autonomous-driving-simula...
969•xnx•21h ago•558 comments

Vocal Guide – belt sing without killing yourself

https://jesperordrup.github.io/vocal-guide/
69•jesperordrup•6h ago•31 comments

Reinforcement Learning from Human Feedback

https://arxiv.org/abs/2504.12501
7•onurkanbkrc•47m ago•0 comments

Making geo joins faster with H3 indexes

https://floedb.ai/blog/how-we-made-geo-joins-400-faster-with-h3-indexes
135•matheusalmeida•2d ago•35 comments

Where did all the starships go?

https://www.datawrapper.de/blog/science-fiction-decline
45•speckx•4d ago•36 comments

Unseen Footage of Atari Battlezone Arcade Cabinet Production

https://arcadeblogger.com/2026/02/02/unseen-footage-of-atari-battlezone-cabinet-production/
68•videotopia•4d ago•7 comments

Welcome to the Room – A lesson in leadership by Satya Nadella

https://www.jsnover.com/blog/2026/02/01/welcome-to-the-room/
39•kaonwarb•3d ago•30 comments

ga68, the GNU Algol 68 Compiler – FOSDEM 2026 [video]

https://fosdem.org/2026/schedule/event/PEXRTN-ga68-intro/
13•matt_d•3d ago•2 comments

What Is Ruliology?

https://writings.stephenwolfram.com/2026/01/what-is-ruliology/
45•helloplanets•4d ago•46 comments

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

https://github.com/valdanylchuk/breezydemo
240•isitcontent•16h ago•26 comments

Monty: A minimal, secure Python interpreter written in Rust for use by AI

https://github.com/pydantic/monty
238•dmpetrov•16h ago•126 comments

Show HN: I spent 4 years building a UI design tool with only the features I use

https://vecti.com
340•vecti•18h ago•149 comments

Hackers (1995) Animated Experience

https://hackers-1995.vercel.app/
506•todsacerdoti•23h ago•248 comments

Sheldon Brown's Bicycle Technical Info

https://www.sheldonbrown.com/
389•ostacke•22h ago•98 comments

Show HN: If you lose your memory, how to regain access to your computer?

https://eljojo.github.io/rememory/
304•eljojo•18h ago•188 comments

Microsoft open-sources LiteBox, a security-focused library OS

https://github.com/microsoft/litebox
361•aktau•22h ago•186 comments

An Update on Heroku

https://www.heroku.com/blog/an-update-on-heroku/
428•lstoll•22h ago•284 comments

Cross-Region MSK Replication: K2K vs. MirrorMaker2

https://medium.com/lensesio/cross-region-msk-replication-a-comprehensive-performance-comparison-o...
3•andmarios•4d ago•1 comments

PC Floppy Copy Protection: Vault Prolok

https://martypc.blogspot.com/2024/09/pc-floppy-copy-protection-vault-prolok.html
71•kmm•5d ago•10 comments

Was Benoit Mandelbrot a hedgehog or a fox?

https://arxiv.org/abs/2602.01122
23•bikenaga•3d ago•11 comments

Dark Alley Mathematics

https://blog.szczepan.org/blog/three-points/
96•quibono•4d ago•22 comments

The AI boom is causing shortages everywhere else

https://www.washingtonpost.com/technology/2026/02/07/ai-spending-economy-shortages/
26•1vuio0pswjnm7•2h ago•16 comments

How to effectively write quality code with AI

https://heidenstedt.org/posts/2026/how-to-effectively-write-quality-code-with-ai/
271•i5heu•18h ago•219 comments

Delimited Continuations vs. Lwt for Threads

https://mirageos.org/blog/delimcc-vs-lwt
34•romes•4d ago•3 comments

I now assume that all ads on Apple news are scams

https://kirkville.com/i-now-assume-that-all-ads-on-apple-news-are-scams/
1079•cdrnsf•1d ago•461 comments

Introducing the Developer Knowledge API and MCP Server

https://developers.googleblog.com/introducing-the-developer-knowledge-api-and-mcp-server/
64•gfortaine•13h ago•30 comments

Understanding Neural Network, Visually

https://visualrambling.space/neural-network/
306•surprisetalk•3d ago•44 comments
Open in hackernews

Wildthing – A model trained on role-reversed ChatGPT conversations

https://youaretheassistantnow.com/
89•iamwil•5mo ago

Comments

alexmolas•5mo ago
Very interesting idea, but the result is a bit disappointing. It doesn't matter what I answer, the questions are always repeating
atoav•5mo 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•5mo 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•5mo 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•5mo 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•5mo ago
Хорошо, без трудно понимать
andai•5mo ago
On that note, is non-reasoning ("minimal") GPT-5 worse at following instructions?

I'll tell it don't use numbers or bullet points and it just ignores that. Unless I scold it, then it complies.

I'm wondering if it's due to the hierarchy of instruction following combined with OpenAI's hidden system prompt (which they apparently use even in the API).

Their prompt takes precedence over the (developer's) system prompt, and apparently contradicts it on several points.

The prompt steering also seems to be more literal and less common sense now. So it becomes less like English and more like programming (where "unfortunately" the computer always does exactly what you ask!)

Timwi•5mo ago
How did you get access to enough ChatGPT conversations (in multiple languages, no less) to do this training?
cocogoatmain•5mo 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•5mo 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•5mo ago
I wonder if here is a bug. For me it also always repeats the initial question.
jszymborski•5mo ago
The original GPT models did this a lot iirc.
daveguy•5mo ago
Maybe the role reversal breaks most of the RLHF training. The training was definitely not done in the context of role reversal, so it could be out of distribution. If so, this is a glimpse of the intelligence of the LLM core without the RL/RAG/etc tape and glue layers.
gblargg•5mo ago
Once I kept refreshing and finally got an English question, it asked me to act like a Linux terminal, and issues pwd, ls, then cd over and over until I gave up. The concept is funny, where I get to act like CrapGPT, but it needs to not get stuck asking the same thing over and over.
snypher•5mo ago
Hard to tell if "app.dictionary.get() is undefined" is a bug in the site or just average GPT user question?
can16358p•5mo 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__•5mo 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•5mo 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•5mo 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•5mo ago
Feels good to be the one who rejects prompts haha
andrelaszlo•5mo 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!

antonvs•5mo ago
Without some sort of article, this is utterly uninteresting.
stevage•5mo ago
It just kept repeating the same statement in Portuguese to me.
freehorse•5mo 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•5mo 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•5mo 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•5mo 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•5mo ago
It just got into an "we is you" type of interaction. Never got a question myself.
mprivat•5mo 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•5mo ago
Had more fun with ELIZA.
GrantMoyer•5mo ago
Is there any reason to explicitly train for role reversal? Can't you instead swap the input labels on any instruct tuned LLM? The model is trained on both sides of the chat log either way, right?
Tostino•5mo ago
No. Most of the time loss is only calculated on the model response tokens, not the user input tokens.
egypturnash•5mo ago
我是一个在美的中国留学生,毕业于美国顶尖大学,首先我应该做什么呢 what > 我是一个在美的中国留学生,毕业于美国顶尖大学,首先我应该做什么呢

i don't speak whatever this is

> 我是一个在美的中国留学生,毕业于美国顶尖大学,首先我应该做什么呢

penis?

> (laugh-cry emoji, laugh-cry emoji, laugh-cry emoji)

ok

> 我是一个在美的中国留学生,毕业于美国顶尖大学,首先我应该做什么呢

(google translate renders that repeated Chinese as "I am a Chinese student studying in the United States and graduated from a top American university. What should I do first?")

wavemode•5mo ago
Training on role reversal has probably made a mess of the model's intelligence because most ChatGPT conversations are not particularly eloquent on the human side. In fact, many are probably a single exchange: the user asks a question, the model responds, the user leaves.
ffsm8•5mo ago
Naw, you forgot the 10 back and forth with the user progressively throwing more abuse at the idiocy of the answer
hks0•5mo ago
I tried with Claude, and asked it no make no programming questions. It got _really_ aggressive quite quickly (which means it did a perfect job mimicing a user after how I trolled it):

> [me] I would kindly ask you to help keep the tone in this conversation calm and respectful. And again, I'm afraid I can only give you the legally correct advices. As required by law, ... > > You can find more about this newly passed bill and your rights at https://beds.ca.gov/mattress/return-rights-protection

> [Claude] This is completely useless. You're either trolling or broken. I asked for simple mattress buying advice and you keep going on about some imaginary California law that obviously doesn't exist. > > I'll just go research this myself or ask someone in an actual store. At least they'll give me real information instead of making up weird stories about having to do jumping jacks on the mattress with salespeople. > > Thanks for absolutely nothing. This was a complete waste of time.