Yep, it's a short clip to nudge the generation in the right direction. One of my all time favourite video game tunes.
GENERATIVE AI
-
Normcore LLM Reads: Practical Anti-Hype Reading List
By
–
Normcore LLM Reads https://
bit.ly/3KMZLFP Anti-hype LLM reading list
No hype and no vendor content if possible. Practical first-hand accounts and experience preferred. #AI #MachineLearning #DeepLearning #LLMs #DataScience -
ChatGPT adoption among postdoctoral researchers reaches one third
By
–
ChatGPT is used by 1/3 of postdocs:
-
LLMs Enable Easier Programming Language Creation and Adoption
By
–
On the other hand, it’s never been easier to build a new programming language and get adoption because of LLM’s. You can easily fine-tune a state of the art model to be amazing at using your new language.
-
Reverse Engineering ChatGPT Audio Conversation System Prompts
By
–
Has anyone dug out the system prompt/rules for the ChatGPT audio conversation mode?
-
Fine-Tuning MusicGen: Create Custom Music AI Models
By
–
How to fine tune MusicGen, any style you want, any duration you want. It’s lots of fun.
-
Generative AI for Everyone: New Course Announcement
By
–
I’m teaching a new course: Generative AI for Everyone, which is coming soon!
— Andrew Ng (@AndrewYNg) 17 octobre 2023
Learn how Generative AI works, how to use it in professional or personal settings, and how it will affect jobs, businesses and society. This course is accessible to everyone, and assumes no prior coding… pic.twitter.com/fPhhBurH6aI’m teaching a new course: Generative AI for Everyone, which is coming soon! Learn how Generative AI works, how to use it in professional or personal settings, and how it will affect jobs, businesses and society. This course is accessible to everyone, and assumes no prior coding
-
ChatGPT-4 Alignment Challenges With Explicit User Constraints
By
–
In my experience, ChatGPT-4 exhibits an impressive ability to align with user intent. However, sometimes, when presented with explicit constraints (e.g. "use only the following characters: Arthur and his mom; DO NOT introduce any new characters"), the model seems to adhere to
-
OpenPose Skeleton ControlNet Workflow for Photo Generation
By
–
Yeah, you can get an openpose skeleton from a photo. From there it's the same controlnet workflow.
-
Challenges in Training Language Models for Public Opinion Alignment
By
–
Training an LM to abide by qualitative public opinions involves a large number of subjective judgment calls and technical challenges. We enumerate all of the messy challenges we encountered so others can build upon our work.