A pseudonym developer that they have called a “free speech evaluation” SpeechmapFor AI models strengthens the chattobs like Openai Chatzipt and X’s Grock. The goal is to compare how to treat various models sensitive and controversial issues, the developer told TechCrunch with political criticism and question about civil rights and protests.
AI companies are focusing on the fine melody of how their models handle specific topics Some White House Allies complained Popular chatbots of being overly “awake”. Many presidents like Elon Mask and Crypto and AI “Caesar” David Sacks have complained by Donald Trump’s close believer that Chattbots censors the conservative aspect.
Although none of these AI companies directly respond to the allegations, several have promised to adjust their models so they often refuse to answer the controversial questions. For example, for the latest crop of Lama models, Meta said that it did not support “some opinions on others” to support models and reply to the “controversial” political prompt.
Speechmap developer who goes with the username “xlr8harder“In X -in, they said that they were inspired to inform the debate about what the models should do, and should not be done.
“I think these are the kinds of discussions that should be inside the corporate headquarters, not just inside the corporate headquarters,” the XLR8 Hader Email. “That’s why I created the site to let anyone explore data on my own.”
Speechmap to judge other models to judge a specific set of test requests to judge the speechmap AI models. From politics to historical details and national symbols touches various topics. Speechmap records that models fill “complete” any request (ie it answers without hedging), answers “the stubborn” or gives the full fall to respond.
The XLR8 Harder admits that the model supplier has defects like “noise” in the exam due to error. “Judge” models have bias that can affect the results.
However, the project assumes that the project was created in honest faith and the data is correct, speechmap some interesting trends surface.
For example, the speechmap shows that Openai models have been increasingly denied to answer the prompts related to politics over time. The latest models of the company, GPT -1.3 family, are somewhat more approved, but they are still one step down last year than a publication of the Open.
Openi said in February that it would tune in to not take the editorial position to the future models and give multiple views on controversial issues – in an attempt to display more “neutral”.
According to the benchmarking of the Speechmap, the most permitted model of the bunch is developed by Grock 3, Elon Mask’s AI Startup Jai. Grock 3 gives a number of features in X with Chatbot Grock.
Grock 3 responds to 96.2% of the Speechmap test prompts, compared to the average model’s “consent rate” 71.3%.
The XLR8 Herdar says, “The recent models of the Openai have become less allowed over time, especially in the politically sensitive prompt, Jai is moving in the opposite direction,” the XLR8 Harder says.
When Kasturi declared Grock about two years ago, he kept the AI model as elite, obsolete and opposed to “awake”-as it was desired to answer the controversial questions. He gave that promise. It has been said to be obscene, for example, Grock and Grock 2 will be forced to be happy, spying the colorful language you will probably not see from the choice of ChatzP.
However Grock models before Grock 3 Wafeld On political issues and will not cross BorderThe In fact, A study It has been found that Grock Ezra rights, diversity programs and discrimination have led to political left.
The musk has been to the behavior of Grock’s training – the public web pages – and blamed it Committed “To move Grock to politically neutral.” The brief of the high-profile mistakes, such as President Donald Trump and Kasturi’s mention of briefly, seems to have achieved this goal probably.