Practical AI: Machine Learning, Data Science
Technology:Software How-To
Recently, we briefly mentioned the concept of “Activation Hacking” in the episode with Karan from Nous Research. In this fully connected episode, Chris and Daniel dive into the details of this model control mechanism, also called “representation engineering”. Of course, they also take time to discuss the new Sora model from OpenAI.
Leave us a comment
Changelog++ members save 4 minutes on this episode because they made the ads disappear. Join today!
Sponsors:
Featuring:
Show Notes:
Something missing or broken? PRs welcome!
Legal consequences of generated content
A developer's toolkit for SOTA AI
Cambrian explosion of generative models
Automated cartography using AI
From ML to AI to Generative AI
AI trends: a Latent Space crossover
Accidentally building SOTA AI
Controlled and compliant AI applications
Data augmentation with LlamaIndex
Creating instruction tuned models
The last mile of AI app development
Large models on CPUs
Causal inference
Capabilities of LLMs 🤯
Computer scientists as rogue art historians
Accelerated data science with a Kaggle grandmaster
Explainable AI that is accessible for all humans
AI search at You.com
End-to-end cloud compute for AI/ML
Success (and failure) in prompting
Create your
podcast in
minutes
It is Free
Podcast – Kitchen Sink WordPress
The Goat Farm
Away From The Keyboard
Arrested DevOps
Build Phase