AI safety takes

Reflections on Brainrot

memetics are destiny

Jul 10 • 

Daniel Paleka

8

May 2025

March-April 2025 safety news: Antidistillation, Cultural alignment, Dark patterns

Happy NeurIPS deadline to all those who celebrate!

May 16 • 

Daniel Paleka

7

1

March 2025

GPT-4o draws itself as a consistent type of guy

When asked to draw itself as a person, the ChatGPT Create Image feature introduced on March 25, 2025, consistently portrays itself as a white male in…

Mar 31 • 

Daniel Paleka

20

11

January-February 2025 safety news: Emergent misalignment, SAE sanity checks, Utility engineering

Some papers I’ve learned something from recently, or where I have takes.

Mar 9 • 

Daniel Paleka

7

January 2025

You should delay engineering-heavy research in light of R&D automation

tl;dr: LLMs rapidly improving at software engineering and math means lots of projects are better off as Google Docs until your AI agent intern can…

Jan 6 • 

Daniel Paleka

11

1

October 2024

September/October 2024 safety news: Jailbreaks on robots, Breaking unlearning, Forecasting evals

Better version of the Twitter newsletter.

Oct 31, 2024 • 

Daniel Paleka

7

August 2024

July/August 2024 safety news: Tamper resistance, Fluent jailbreaks, Scaling limits

Better version of the Twitter newsletter.

Aug 31, 2024 • 

Daniel Paleka

5

July 2024

May/June 2024 safety news: Out-of-context reasoning, Sparse autoencoders, Interpreting CLIP

Better version of the Twitter newsletter.

Jul 1, 2024 • 

Daniel Paleka

4

April 2024

March/April 2024 safety news: Latent training, Emergent abilities, Instruction hierarchy

Better version of the Twitter newsletter.

Apr 30, 2024 • 

Daniel Paleka

5

4

February 2024

January/February 2024 safety news: Sleeper agents, In-context reward hacking, Universal neurons

Better version of the Twitter newsletter.

Feb 29, 2024 • 

Daniel Paleka

4

1

December 2023

November/December 2023 safety news: Weak-to-strong generalization, Superhuman concepts, Google-proof benchmark

Better version of the Twitter newsletter.

Dec 27, 2023 • 

Daniel Paleka

5

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.

Oct 17, 2023 • 

Daniel Paleka

3