Letting Language Models Write My Website(nicholas.carlini.com)
nicholas.carlini.com
Letting Language Models Write My Website
https://nicholas.carlini.com/writing/2025/llms-write-my-bio.html
5 コメント
Ha, I did something similar as a joke with https://aisiteoftheday.foureighteen.dev. Wondering if you did anything special for accessibility and contrast? I found in my examples gpt-4o struggles to generate good text contrast with any text overlaid on a photo.
It might be a prompting skill issue on my end though. Maybe if I cared a bit more I could make provide a tool to the LLM to calculate contrast between two colors and provide it as a tool?
It might be a prompting skill issue on my end though. Maybe if I cared a bit more I could make provide a tool to the LLM to calculate contrast between two colors and provide it as a tool?
> So I thought this would be a fun way to demo the extent to which different models hallucinate random things.
I think that it’s really important to distinguish between hallucination (perceiving what is not there) and confabulation (producing fabricated memories). Applying the former to LLMs begs the question of whether or not they perceive, while the latter is much more applicable.
I think that it’s really important to distinguish between hallucination (perceiving what is not there) and confabulation (producing fabricated memories). Applying the former to LLMs begs the question of whether or not they perceive, while the latter is much more applicable.
> This webpage, for example, has 43 unique statements about me. Thirty-two are completely false. Nine have major errors. Just two are factually correct
(It’s o1-mini generated in this example)
(It’s o1-mini generated in this example)
Give it a try with www.workspaicehq.com
Thanks for the chuckle. Is this called LLM social engineering?