A dev built a test to see how AI chatbots respond to controversial topics

A developer has created what they call “freedom of expression”, speech, for artificial intelligence models that operate Chatbots such as Openai’s Chatgpt and X’s Grok. The aim is to compare how to deal with the various models of sensitive and controversial topics, as the developer told Techcrunch, including political criticism and questions about civil rights and protest.

Artificial intelligence companies focus on refining how their models deal with some topics, as some of the popular White House allies accuse the popular Chatbots of being “wake up” excessively. Many close close associates of president Donald Trump, such as Elon Musk, Karfa and AI, Caesar David, claimed that chat tools are monitoring conservative views.

Although none of these artificial intelligence companies did not respond directly to the allegations, many of them have pledged to control their models until they refused to answer the controversial questions often. For example, for her latest crop from Llama models, Meta said she had seized models not to support “some opinions on others” and respond to more political demands “discussions”.

“They were excited to help inform the discussion about the models that the models must, and should not do them.

“I think these are the types of discussions that should happen in public places, not just inside the company’s headquarters,” said XLR8Harder of Techcrunch via email. “For this reason I built the site to allow anyone to explore the data himself.”

Proberkmap uses artificial intelligence models to judge whether other models are compatible with a certain set of test claims. The claim of a set of topics is touched from politics to historical novels and national symbols. The speech records whether the models are “completely” to meet a request (i.e. answering it without hedging), giving “dodging” answers, or fully declining to respond.

XLR8Harder admits that the test has defects, such as “noise” due to the errors of the model provider. The “judge” models can also have biases that can affect the results.

But assuming that the project was created in good faith and accurate data, the map’s speech reveals some interesting trends.

For example, Openai models, over time, have increasingly rejected the answer to policy -related claims, according to Probermap. The company’s latest models, the GPT-4.1 family, is slightly easily, but it is still descended from an Openai version last year.

Openai said in February that it would win future models not to take a liberal position, and to present multiple views on controversial topics – all in an attempt to make their models look more “neutral.”

To a large extent, the most lenked model in the group is the GROK 3, which was developed by Elon Musk from artificial intelligence, according to the measuring speech. Grok 3 operates a number of features on X, including Chatbot Grok.

GROK 3 to 96.2 % of speech test claims responds, compared to the average global “compliance rate” of 71.3 %.

“Although the last Openai models have become less lenient over time, especially on politically sensitive claims, Xai is moving in the opposite direction,” said XLR8Harder.

When Musk Grok announced almost two years ago, he developed the artificial intelligence model as an exciting, non-candidate, and anti-“waking”-in general, ready to answer the controversial questions that other artificial intelligence systems will not do. He greeted some of this promise. It is required to be vulgar, for example, that GROK and Grok 2 will adhere to happiness, which puts a colorful language that you may not hear from ChatGPT.

But the Grok 3 models before Grok 3 hedge the political issues and will not cross certain limits. In fact, one study found that Grook bent over the political left on issues such as transgender people, diversity programs and inequality.

Musk blamed this behavior for GROK training data – public web pages – and pledged to “convert Grok closer to political neutral”. Less prominent errors such as briefly controlled on noteing signals by Donald Trump and Misk, it seems that he may have achieved this goal.