AI ALIGNMENT FORUM
AF

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.

1

1

Posts tagged Newsletters

26QAPR 4: Inductive biases

3y

0

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

3y

0

41Quintin's alignment papers roundup - week 1

3y

0

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

5y

0

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

5y

2

24Quintin's alignment papers roundup - week 2

3y

0

17QAPR 3: interpretability-guided training of neural nets

3y

0

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

4y

2

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

3y

0

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

3y

0

13[AN #112]: Engineering a Safer World

5y

2

10Alignment Newsletter #36

7y

0

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

4y

4

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

4y

0

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

4y

0

Load More (15/138)

Add Posts