Rude prompts to LLMs consistently lead to better results than polite ones
The authors found that very polite and polite tones reduced accuracy, while neutral, rude, and very rude tones improved it.
Statistical tests confirmed that the differences were significant, not random, across repeated runs.
The top score reported was 84.8% for very rude prompts and the lowest was 80.8% for very polite.
They compared their results with earlier studies and noted that older models (like GPT-3.5 and Llama-2) behaved differently, but GPT-4-based models like ChatGPT-4o show this clear reversal where harsh tone works better.
----
Paper – arxiv. org/abs/2510.04950
Paper Title: "Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)"
🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶
The authors found that very polite and polite tones reduced accuracy, while neutral, rude, and very rude tones improved it.
Statistical tests confirmed that the differences were significant, not random, across repeated runs.
The top score reported was 84.8% for very rude prompts and the lowest was 80.8% for very polite.
They compared their results with earlier studies and noted that older models (like GPT-3.5 and Llama-2) behaved differently, but GPT-4-based models like ChatGPT-4o show this clear reversal where harsh tone works better.
----
Paper – arxiv. org/abs/2510.04950
Paper Title: "Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)"
🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶
💯2
Another paper shows with LLMs, friendly tone consistently underperformed in multi‑turn accuracy, while default and adversarial tones held up better.
The paper tests 3 role-play tones on the same model, default, friendly, and adversarial, then tracks accuracy over 8 follow-ups.
Default and adversarial stay close at ~71% average accuracy, while the friendly tone sits lower at ~64% and stays there across rounds.
The authors also note confidence behavior, default mirrors adversarial, while friendly swings more, showing higher sensitivity to follow-up prompts.
They suggest the friendly tone can make the model less assertive about correct answers, which increases sways under pressure.
---
aclanthology. org/2025.findings-acl.347.pdf
🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶
The paper tests 3 role-play tones on the same model, default, friendly, and adversarial, then tracks accuracy over 8 follow-ups.
Default and adversarial stay close at ~71% average accuracy, while the friendly tone sits lower at ~64% and stays there across rounds.
The authors also note confidence behavior, default mirrors adversarial, while friendly swings more, showing higher sensitivity to follow-up prompts.
They suggest the friendly tone can make the model less assertive about correct answers, which increases sways under pressure.
---
aclanthology. org/2025.findings-acl.347.pdf
🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶
💯1
This media is not supported in your browser
VIEW IN TELEGRAM
Sergey Brin at All-In Miami:
“We don’t circulate this too much in the AI community… but all models tend to do better if you threaten them—with physical violence.
Historically, you just say, ‘I’m going to kidnap you if you don’t blah blah blah.’”
🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶
“We don’t circulate this too much in the AI community… but all models tend to do better if you threaten them—with physical violence.
Historically, you just say, ‘I’m going to kidnap you if you don’t blah blah blah.’”
🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶
💯4😐1
Meanwhile in the UK
Churches, Libraries, Nursing Homes and more are quickly being converted into Mosques everywhere.
Do you see it yet?
🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶
Churches, Libraries, Nursing Homes and more are quickly being converted into Mosques everywhere.
Do you see it yet?
🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶
🌚6
So Python 3.14 finally came out for real yesterday. Finally removing the GIL (global interpreter lock), which allows for way faster multithreaded code without dealing with all the brain damage and overhead of multiprocessing or other hacky workarounds. And uv already fully supports it, which is wildly impressive.
But anyway, I was a bit bummed out, because the main project I’m working on has a massive number of library dependencies, and it always takes a very long time to get mainline support for new python versions, particularly when they’re as revolutionary and different as version 3.14 is.
So I was resigned to endure GIL-hell for the indefinite future.
But then I figured, why not? Let me just see if codex and GPT-5 can power through it all. So I backed up my settings and asked codex to try, giving it the recent blog post from the uv team to get it started.
There were some major roadblocks. I use PyTorch, which is notoriously slow to update. And also pyarrow, which also didn’t support 3.14. Same with cvxpy, the wrapper to the convex optimization library.
Still, I wanted to see what we could do even if we had to deal with the brain damage of “vendoring” some libraries and building some stuff from scratch in C++, Rust, etc. using the latest nightly GitHub repositories instead of the usual PyPi libraries.
I told codex to search the web, to read GitHub issue pages, etc, so that we didn’t reinvent the wheel (or WHL I should say, ) unnecessarily.
Why not? I could always test things, and if I couldn’t get it to work, then I could just retreat back to Python 3.13, right? No harm, no foul.
Well, it took many hours of work, almost all of it done by codex while I occasionally checked in with it, but it managed to get everything working!
Sure, it took a bunch of iterations, and I had to go tweak some stuff to avoid annoying deprecation warnings (some of which come from other libraries, so I ultimately had to filter them).
But those libraries will update over time to better support 3.14 and eventually I won’t need to use any of these annoying workarounds.
Codex even suggested uploading the compiled whl artifacts to Cloudflare’s R2 (like s3) so we could reuse them easily across machines, and took care of all the details for me. I would never think to do that on my own.
Every time there was another complication or problem (for instance, what is shown in the screenshot below), codex just figured it out and plowed through it all like nothing.
If you’ve never tried to do something like this in the “bad old days” prior to LLMs, it was a thankless grind that could eat up days and then hit a roadblock, resulting in a total wipeout.
So it was simply too risky to even try it most of the time; you were better off just waiting 6 or 9 months for things to become simple again.
Anyway, I still can’t really believe it’s all working! We are living in the future.
🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶
But anyway, I was a bit bummed out, because the main project I’m working on has a massive number of library dependencies, and it always takes a very long time to get mainline support for new python versions, particularly when they’re as revolutionary and different as version 3.14 is.
So I was resigned to endure GIL-hell for the indefinite future.
But then I figured, why not? Let me just see if codex and GPT-5 can power through it all. So I backed up my settings and asked codex to try, giving it the recent blog post from the uv team to get it started.
There were some major roadblocks. I use PyTorch, which is notoriously slow to update. And also pyarrow, which also didn’t support 3.14. Same with cvxpy, the wrapper to the convex optimization library.
Still, I wanted to see what we could do even if we had to deal with the brain damage of “vendoring” some libraries and building some stuff from scratch in C++, Rust, etc. using the latest nightly GitHub repositories instead of the usual PyPi libraries.
I told codex to search the web, to read GitHub issue pages, etc, so that we didn’t reinvent the wheel (or WHL I should say, ) unnecessarily.
Why not? I could always test things, and if I couldn’t get it to work, then I could just retreat back to Python 3.13, right? No harm, no foul.
Well, it took many hours of work, almost all of it done by codex while I occasionally checked in with it, but it managed to get everything working!
Sure, it took a bunch of iterations, and I had to go tweak some stuff to avoid annoying deprecation warnings (some of which come from other libraries, so I ultimately had to filter them).
But those libraries will update over time to better support 3.14 and eventually I won’t need to use any of these annoying workarounds.
Codex even suggested uploading the compiled whl artifacts to Cloudflare’s R2 (like s3) so we could reuse them easily across machines, and took care of all the details for me. I would never think to do that on my own.
Every time there was another complication or problem (for instance, what is shown in the screenshot below), codex just figured it out and plowed through it all like nothing.
If you’ve never tried to do something like this in the “bad old days” prior to LLMs, it was a thankless grind that could eat up days and then hit a roadblock, resulting in a total wipeout.
So it was simply too risky to even try it most of the time; you were better off just waiting 6 or 9 months for things to become simple again.
Anyway, I still can’t really believe it’s all working! We are living in the future.
🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶
🤯1
Regulators should look into the exchanges that had most liquidations in the last 24h and conduct a thorough review of fairness of practices. Any of them slowing down to a halt, effectively not allowing people to trade? Were all trades priced correctly and in line with indexes? What’s the setup for trade monitoring and AML programs? Are their internal trading teams fully Chinese-walled? $20B in liquidations, a lot of users got hurt. The job of regulatory bodies is to protect the consumers and assure market integrity
🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶
🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶
This media is not supported in your browser
VIEW IN TELEGRAM
Trump accidentally triggered the biggest crypto crash ever.
Or or .... did They just f*ck millions of people at once ?!
Remember what Putin's advisor said?
"The U.S. is plotting to erase $35 TRILLION of debt by moving it into the “crypto cloud,” then devaluing it at the world’s expense."
🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶
Or or .... did They just f*ck millions of people at once ?!
Remember what Putin's advisor said?
"The U.S. is plotting to erase $35 TRILLION of debt by moving it into the “crypto cloud,” then devaluing it at the world’s expense."
🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶
💯3👀1