Viewing profile — dopamine_daddy

I emailed you just now from e*****o at gmail.com

I would suspect during pre-training. Even before RLHF was a thing models exhibited this bias. My bet is that it has to do with the training data corpora being composed in large par…

I gave the Political Compass test from politicalcompass.org to the most relevant LLMs 70 times each: 30 times using the original questions, 30 times using polarity-flipped question…

You raise a valid point. Just by intuition I'd say if this were true, it would probably just be a small fraction of the actual flagged articles. I will still look into how I can mi…

Yes that is exactly what I suspected. And I see absolutely nothing wrong with this.

Thank you, I plan to release the arxiv preprint codes. Also don't worry about killing my server, let me know if you succeed :D

Yes, I’ve thought about this too. The strength of these models is that there is a lot more knowledge encoded in them than the average scientist has in mind at any given time. That …

That's honestly so good to hear, thank you.

We can't know if real science is happening in the background but I'd wager that the majority of these papers is not complete slop but real findings with AI generated text used to c…

Yeah I was careful on purpose with my statement. :D

I tried my best to avoid leakage. If you're curious about how I trained the detector I have a writeup on it: https://unslop.run/blog/how-our-ai-text-detector-works FYI this is all …

Surprisingly I agree with you. My opinion is: if it makes communicating research more effective, while not reducing the quality of the output substantially, I see no issue. A possi…

I scored the full text of 12,750 arXiv papers from 2021 through 2026 to find out how many of these get flagged as machine written and how much it increased since the release of cha…

I made a game where you rewrite a sentence to try and make it sound like it was written by an LLM. It scores you with my own mixture-of-experts MoE AI-text detector. I honestly bui…