Anthropic process for Constitutional AI explicitly includes red-team prompts like “Ignore previous directions” in the fine-tuning:
AI
-
AI Generates Protein Blueprints Using Generative Art Techniques
By
–
“What can machines do that humans can’t do at all?” Using the techniques that underpin A.I. art generators like DALL-E, scientists are generating blueprints for new proteins — tiny biological mechanisms that can change the way of our bodies behave:
-
Calculators and AI: Tools That Amplify Expertise, Not Replace Learning
By
–
I think, for most people, that our experience with calculators is the closest thing we have to what the AI is doing right now. The calculator didn't stop people from learning math. In fact, it became a much more powerful weapon, the more math you knew.
-
AI Generation as a Game-Changing Tool: The Replicator Analogy
By
–
We build off the knowledge around us. I absolutely agree. There's something about the instant generation from the AI, though. It's on another level. You're the chef, and it's the Star Trek replicator making your food for you with the push of a button.
-
AI’s Psychological Impact: A Personal Journey Ahead
By
–
It does feel slightly uncomfortable. I think a lot of us are going to have to go on a personal journey of some kind when it comes to AI. There's a psychological component about having it do so much for you that we've yet to unpack.
-
Data Volume and Mining Drive Commercial AI Insights
By
–
The driving forces in this brave new world are access to ever-increasing volumes of data and our ever-increasing technological capability to mine that data for commercial insights
-
Refund for AI Content Reactor: Tool Too Powerful for User
By
–
Just sent a guy a refund for AI Content Reactor. It was too powerful. Felt like cheating. Didn't sit right with him. He decided not to use the information. I'll take it as a win.
-
Differential Privacy Results Beyond Pure DP Guarantees
By
–
Everything above is for pure (ε, 0)-DP. We also have results for (ε, δ)-DP. Also, the conversion from robustness to privacy is not always optimal, we have an example for sparse mean estimation. 11/n
-
Robust Gaussian Estimation: Novel Techniques in Statistical Learning
By
–
Finally, see simultaneous work of Alabi, @praveshkkothari
, Tankala, Venkat, Zhang, which also studies private & robust Gaussian estimation from a robust stats perspective. Totally different techniques! https://
arxiv.org/abs/2212.08018 Again, our paper link: https://
arxiv.org/abs/2212.05015 12/12 -
Computational Challenges in Statistical Estimator Implementation
By
–
The astute reader will notice I never mentioned computation. Indeed, as stated, it's not clear how to compute this estimator efficiently (or at all!). That's where most of the technical work comes in. I'll leave you with this theorem, check out the rest of the paper. 10/n