Do LLMs hold the opinions they give you?
The article discusses whether large language models (LLMs) hold the opinions they provide to users. The author conducted an experiment to test this by interacting with Claude, ChatGPT, and Gemini. The results of the experiment are not specified in the provided text, but the author's goal was to determine if these models have real positions or just simulate opinions.
- ▪The author spent a weekend testing LLMs to see if they hold real opinions.
- ▪The experiment involved interacting with Claude, ChatGPT, and Gemini.
- ▪The author's goal was to determine if these models have genuine positions or just sound like they do.
Opening excerpt (first ~120 words) tap to expand
Marut Pandya@pandya_marutArticleDo LLMs actually hold the opinions they give you?I spent a weekend testing whether Claude, ChatGPT, and Gemini have real positions — or just sound like they do. This started as a thought experiment I'd been turning over for a while, and one weekend...11:15 PM · May 17, 202677Views:host{display:inline-block;direction:ltr;white-space:nowrap;line-height:var(--number-flow-char-height, 1em) !important}span{display:inline-block}:host([data-will-change]) span{will-change:transform}.number,.digit{padding:round(nearest, calc(var(--number-flow-mask-height, 0.25em) / 2), 1px) 0}.symbol{white-space:pre}1number-flow-react > span{font-kerning:none;display:inline-block;line-height:var(--number-flow-char-height, 1em) !important;padding:calc(round(nearest,…
Excerpt limited to ~120 words for fair-use compliance. The full article is at X (formerly Twitter).
Discussion
0 commentsMore from X (formerly Twitter)
