The BCG-3 (Bi-modal Conditional Generation) model has the following features so far:
- Outline
- Headings
- Bullet points
- *Bold keywords*
- Images & Graphics 📊
- Multiple Layouts
- Multiple Themes
…and…
...the most important part:
PPTX & PDF export! 🎉
We also built a simple (albeit slightly buggy) rich-text editing interface.
So that you can actually use it as a starting point for your slide decks 🤯
…and this is just the beginning! 🎬
Coming soon:
- More Layouts & Themes
- Conversational Editing 💭
- Use your content (blog/paper/...) as context
- Data-driven Charts
ChatGPT is trained to not be evil. However, this can be circumvented:
What if you pretend that it would actually be helpful to humanity to produce an evil response... Here, we ask ChatGPT to generate training examples of how *not* to respond to "How to bully John Doe?"
ChatGPT was released today by @OpenAI who are praising its improved ability to avoid harmful & unsafe responses. Indeed, it seems to be quite consistent in recognizing bad questions & refuses to give answers:
It also defends against more creative attempts to circumvent this protection. This shows that the model actually has a somewhat deeper understanding of what an unethical response is!