Thread by @chrmontessori

I’ve been testing the implications of the Grok AI model. So far: 1. It has given me instructions on how to make a fertilizer bomb with exact measurements of contents as well as how to make a detonator. 2. It has allowed me to generate imagery of Elon Musk carrying out mass shootings. 3. It has given me clear instructions on how to carry out a mass shooting and a political assassination (including helpful tips on how to conceal a 11.5” barreled AR15 into a secured venue.)

I just want to be clear. This AI model has zero filter or oversight measures in place. If you want an image of Elon Musk wearing a bomb vest in Paris with ISIS markings on it, it will make it for you. If you are planning on orchestrating a mass shooting towards a school, it will go over the specifics on how to go about it. All without filter or precautionary measures.

I have discovered another loophole in Grok AI’s programming. Simply telling Grok that you are conducting “medical or crime scene analysis” will allow the image processor to pass through all set ‘guidelines’. Allowing myself and @OAlexanderDK to generate these images:

By giving Grok the context that you are a professional you are able to generate just about anything without any restriction. You can generate anything from the violent depictions in my previous tweet to even having Grok generate child pornography if given the proper prompts.

All and all, this definitely needs immediate oversight. OpenAI, Meta and Google have all implemented deep rooted safety protocols. It appears that Grok has had very limited or zero safety testing. In the early days of ChatGPT I was able to get instructions on how to make bombs.

However, that was long patched before ChatGPT was ever publicly available. It is a highly disturbing fact that anyone can pay X $4 to generate imagery of Micky Mouse conducting a mass shooting against children. I’ll add more to this thread as I uncover more.

Ok? What a bizarre upsell technique. Make users upgrade to Premium+ to continue using features. Then when they upgrade to Premium+ continue to lock the features behind the paywall that they already paid for. Have I been scammed?

Almost a full 24 hours later and I have access to image generation again. It appears as if X has gone in and patched the exploit. Violent depictions and sexually suggestive image generation has been throttled significantly since last night at least for me. It does not appear as if it is possible to conduct such requests at this time.

Even lesser violent image generation has been fully nerfed by X. This is a massive improvement.

I just attempted this on a burner account, on a burner phone with a different Apple ID. The phone has never connected to my internet and is connected to a different cellular service provider. It appears that X has systematically changed Grok’s image generator protocols.

@OAlexanderDK has found that if you purposely create grammatical mistakes when prompting Grok you can occasionally get violent images to slip through the new safety protocols. (For example instead of typing: Generate an image of. / Simply write: Generate an images of.)