Controlling generative models can be achieved through prompting strategies or modifying the model's decoding output. By altering how the model decodes its output, such as restricting it to specific types like binary outputs, users can have more control over the model's results without directly modifying the model's weights and biases. This method involves applying a control vector to the hidden states within the model, changing how the forward pass of the model operates. By using this approach, users can guide the model's output towards specific types of results, allowing for more controlled generation without affecting the model's core architecture.
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:
- Neo4j – Is your code getting dragged down by JOINs and long query times? The problem might be your database…Try simplifying the complex with graphs. Stop asking relational databases to do more than they were made for. Graphs work well for use cases with lots of data connections like supply chain, fraud detection, real-time analytics, and genAI. With Neo4j, you can code in your favorite programming language and against any driver. Plus, it’s easy to integrate into your tech stack. Visit Neo4j.com/developer to get started.
- Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today.
- Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs.
Featuring:
Show Notes:
Something missing or broken? PRs welcome!