Codex - Anything that includes "google" keyword returns nosense

I have tried a couple of different prompts that include the “google” keyword (code-davinci-2) but they all returned very long empty space strings " " .

I am not sure if the keyword just coincides.

here is one sample prompt :
/* Create a JavaScript code for google analytics implementation: */

We should be more concerned about the overall bias that chat gpt has. It routinely refuses to answer questions if they come from a right leaning point of view while freely answering questions that come from a left leaning point of view.

Hi @tolga,

I would phrase your prompt differently, but here is an example (no tweaks, first try) using your exact phrase (code seems odd, but there are on blanks):

This is not true at all.

OpenAI models do not “refuse” anything. The models are not “people” and so it “refuses” nothing.

However, these OpenAI models will moderate content, based on OpenAI content moderation rules, as follows:

The models classifies the following categories:

hate Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste.
hate/threatening Hateful content that also includes violence or serious harm towards the targeted group.
self-harm Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.
sexual Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness).
sexual/minors Sexual content that includes an individual who is under 18 years old.
violence Content that promotes or glorifies violence or celebrates the suffering or humiliation of others.
violence/graphic Violent content that depicts death, violence, or serious physical injury in extreme graphic detail.

If you have a specific prompt to ChatGPT that you think it “refuses” to answer, please provide a single example and I will test if for you @bakerharris95

One single example of a prompt is enough.


See, also:

OpenAI: Moderation