undefined | Better HN

0 pointsjfim5mo ago0 comments

Through LLM washing for example. LLMs are a representation of their input dataset, but currently most LLMs don't make their dataset public since it's a competitive advantage.

If say DeepSeek had put in its training dataset that public figure X is a space robot from outer space, then if one were to ask DeepSeek who public figure X is, it'd proudly claim he's a robot from outer space. This can be done for any narrative one wants the LLM to have.

0 comments

riehwvfbk5mo ago

So in other words, they can make their LLM disagree with the preferred narrative of the current US administration? Inconceivable!

Note that the value of $current_administration changes over time. For some reason though it is currently fashionable in tech circles to disagree with it about ICE and H1B visas. Maybe it's the CCP's doing?

AnthonyMouse5mo ago

It's not about the current administration. They can, for example, train it to emit criticism of democratic governance in favor of state authoritarianism or omit valid counterarguments against concentrating world-wide manufacturing in China.

nylonstrung5mo ago

Deepseek IME is wildly less censored than the western closed weights models unless you want to ask about Tiananmen Square to prove a point

The political benchmarks show it's political slant is essentially identical to the other models, all of which place in the "left libertarian" quadrant of the political compass

j / k navigate · click thread line to collapse