Newsletters

Edited by Multicore, Rohin Shah last updated 3rd Sep 2020

Newsletters are collected summaries of recent events, posts, and academic papers.

The most prolific newsletter on Less Wrong is Rohin Shah's weekly Alignment Newsletter.

Posts tagged Newsletters

5

26QAPR 4: Inductive biases

Quintin Pope

3y

0

1

10[MLSN #8] Mechanistic interpretability, using law to inform AI alignment, scaling laws for proxy gaming

Dan H, TW123

3y

0

2

41Quintin's alignment papers roundup - week 1

Quintin Pope

3y

0

1

19[AN #102]: Meta learning by GPT-3, and a list of full proposals for AI alignment

Rohin Shah

5y

0

1

13[AN #115]: AI safety research problems in the AI-GA framework

Rohin Shah

5y

2

1

24Quintin's alignment papers roundup - week 2

Quintin Pope

3y

0

1

17QAPR 3: interpretability-guided training of neural nets

Quintin Pope

3y

0

1

26[AN #166]: Is it crazy to claim we're in the most important century?

Rohin Shah

4y

2

0

21[AN #173] Recent language model results from DeepMind

Rohin Shah

3y

0

1

13[MLSN #6]: Transparency survey, provable robustness, ML models that predict the future

Dan H

3y

0

1

13[AN #112]: Engineering a Safer World

Rohin Shah

5y

2

1

10Alignment Newsletter #36

Rohin Shah

7y

0

1

18[AN #167]: Concrete ML safety problems and their relevance to x-risk

Rohin Shah

4y

4

1

15[AN #170]: Analyzing the argument for risk from power-seeking AI

Rohin Shah

4y

0

1

12[AN #145]: Our three year anniversary!

Rohin Shah

5y

0

AI ALIGNMENT FORUM
AF

AI ALIGNMENT FORUM
AF

Newsletters