AI safety takes

Home
Archive
About
January/February 2024 safety news: Sleeper agents, In-context reward hacking, Universal neurons
Better version of the Twitter newsletter. A StrongREJECT for Empty Jailbreaks Jailbreaks in LLMs and adversarial examples in computer vision NNs of yore…
 • 
Daniel Paleka
1

December 2023

November/December 2023 safety news: Weak-to-strong generalization, Superhuman concepts, Google-proof benchmark
Better version of the Twitter newsletter. Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero Superhuman AI will use…
 • 
Daniel Paleka

October 2023

September/October 2023 safety news: Sparse autoencoders, A is B is not B is A, Image hijacks
Better version of the Twitter thread. Thanks to Fabian Schimpf and Charbel-Raphaël Segerie for feedback. Towards Monosemanticity: Decomposing Language…
 • 
Daniel Paleka

August 2023

August 2023 safety news: Universal attacks, Influence functions, Problems with RLHF
Better version of the monthly Twitter thread. This post marks a one-year anniversary since I decided to make use of my paper-reading habit, and started…
 • 
Daniel Paleka
Evaluating superhuman models with consistency checks
Trying to extend the evaluation frontier
 • 
Daniel Paleka
4

July 2023

June/July 2023 safety news: Jailbreaks, Transformer Programs, Superalignment
Better version of the monthly Twitter thread. Will be back to the regular release frequency next month. Thanks to Charbel-Raphaël Segerie for the…
 • 
Daniel Paleka

June 2023

May 2023 safety news: Emergence, Activation engineering, GPT-4 explains GPT-2 neurons
Better version of the monthly Twitter thread. The last weeks have had unusually many cool papers and posts, not all of which I had time to check out…
 • 
Daniel Paleka
3

April 2023

April 2023 safety news: Supervising AIs improving AIs, LLM memorization, OpinionQA
Better version of the monthly Twitter thread. Emergent and Predictable Memorization in Large Language Models Memorization in LLMs is a practical issue…
 • 
Daniel Paleka

March 2023

March 2023 safety news: Natural selection of AIs, Waluigis, Anthropic agenda
Better version of my Twitter newsletter. I’m not talking about any of the recent letters here. This is not an AI policy newsletter. For the record, I…
 • 
Daniel Paleka
Language models rely on meaningful abstractions
Next-token prediction is AI-complete
 • 
Daniel Paleka

February 2023

February 2023 safety news: Unspeakable tokens, Bing/Sydney, Pretraining with human feedback
Better version of the monthly Twitter thread. More than you've asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to…
 • 
Daniel Paleka

January 2023

January 2023 safety news: Watermarks, Memorization in Stable Diffusion, Inverse Scaling
Better version of the monthly Twitter thread. Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge…
 • 
Daniel Paleka
© 2024 Daniel Paleka
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great culture