The prompts that "should be illegal" were all weaksauce. I've got a few prompts that you could maybe say should be illegal and they're like 2 pages long and do hours of work for you in one go
AI
-
Salesforce Customers Unmoved by Slack Acquisition, Analysts Report
By
–
Salesforce Customers Not Swayed by Slack, Analysts Say
@Carhartt
#CIO Katrina Agusti, who uses @Salesforce clouds, said the Slack acquisition has so far not made Salesforce more useful
@lizherbert
@tcrawford
@angusloten
-
ChatGPT and Other AI Writing Tools Comparison
By
–
ChatGPT is the most capable right now, but I like some other tools by http://
Mem.ai and http://
Jasper.ai and the Notion writing assistant as well https://
openai.com/blog/chatgpt/ -
Midjourney Basic Parameters: Version Quality Aspect Ratio
By
–
#13 BASIC PARAMETERS If you analyze some of my prompts, you'll see that I regularly use these parameters: –v : Selects which version of MJ to use. –q : If you want more or less quality. –ar : The proportions of the image. There are more parameters; we'll go over
-
Securing AI Prompts: Leak Prevention and ChatGPT Updates
By
–
Look for all the possible ways in which prompt can be leaked and try to rectify that by imposing programatic filters. A brilliant example is how @OpenAI improved the security of ChatGPT with the recent update so that even with tweaking of input you can’t get the source prompt.
-
Negative Context Issues and Topic Removal Solutions
By
–
Same issues no matter how you word it. If you bring up a topic in any negative context, you might get a positive result on the same topic. Best way around it is giving a task to explicitly remove that topic.
-
OpenAI Beta Duration and Data Collection Strategy
By
–
Really hard to guess. Some of the original OpenAI betas lasted months or maybe even longer than a year if I recall. But with the technology being where it's at, they can start charging anytime they want. Right now they want more training data for how it gets used instead.
-
Negative Prompting in AI Art Tools and Chat Solutions
By
–
With AI art tools, there's this concept of negative prompting where you have a whole separate prompt for what not to put in the image. I imagine chat-based solutions will get better at this in not too long, as some kind of standard way to tell it no emerges
-
Midjourney Parameters: Configuring Quality and Aspect Ratios
By
–
#12 PROMPTS Y PARÁMETROS Volvamos a la construcción del prompt, y vamos a centrarnos en la parte amarilla: LOS PARÁMETROS. Esto son configuraciones que podemos añadir al prompt para modificar el comportamiento de Midjourney. Podemos variar calidad, aspect-ratios, …
-
Securing AI Applications Against Prompt Injection Attacks
By
–
It’s is a burgeoning area of interest on how yo make your application full proof to prompt leaks or any kind of prompt injection attacks. Some remedies are making sure that people can’t easily get to your source prompt (secret sauce) by tweaking with the input.