How to Prompt Inject through Images
Why prompt injecting through images works as a jailbreak, even for GPT 5, and how you can test on your own GPTs.
Sagger Khraishi
70 postsWith 16+ years in marketing, startups, SaaS and Fintech, I founded 4Fsh to help make sure nobody gets fired for not knowing how to use AI.
New Jailbreak for GPT-5
It shouldn't be this easy to jailbreak GPT-5, but here we are with a new injection technique.
Feel like you write like an AI? You kind of are...
If you use AI to write the first draft, and then edit... There's bad news - backed by science.
Why AI Just Can't Fix that Bug
The steps between feeling like a Prompting God to feeling like you are being gas lit by an AI is roughly 7 steps.
Invisible Unicode is what flags your content as AI-generated
It's not having an em-dash that screams AI generated. It's the invisible Unicode that gets dropped off when you generate.
When the model hallucinates, and you didn't know
Models will hallucinate. Sometimes when you are demoing the model like what happened at the OpenAI demo for GPT-5.
How to find your AI API keys
Learn where to get your API keys for OpenAI, Anthropic, and Perplexity, so you can connect it to your automation.
How NOT to find your AI API keys
Where you shouldn't be finding your private API key. The public internet.
Subscribe to new posts
Processing your application
Please check your inbox and click the link to confirm your subscription
There was an error sending the email