Human-AI Safety

TagLast edit: Jul 17, 2023, 11:19 PM by Wei Dai

Three AI Safety Related Ideas

Wei DaiDec 13, 2018, 9:32 PM

69 points

38 comments2 min readLW link

Morality is Scary

Wei DaiDec 2, 2021, 6:35 AM

228 points

116 comments4 min readLW link 1 review

A broad basin of attraction around human values?

Wei DaiApr 12, 2022, 5:15 AM

114 points

18 comments2 min readLW link

Two Neglected Problems in Human-AI Safety

Wei DaiDec 16, 2018, 10:13 PM

102 points

25 comments2 min readLW link

SociaLLM: proposal for a language model design for personalised apps, social science, and AI safety research

Roman LeventovDec 19, 2023, 4:49 PM

17 points

5 comments3 min readLW link

Let’s ask some of the largest LLMs for tips and ideas on how to take over the world

Super AGIFeb 24, 2024, 8:35 PM

1 point

0 comments7 min readLW link

[Question] Will OpenAI also require a “Super Red Team Agent” for its “Superalignment” Project?

Super AGIMar 30, 2024, 5:25 AM

2 points

2 comments1 min readLW link

“Toward Safe Self-Evolving AI: Modular Memory and Post-Deployment Alignment”

Manasa DwarapureddyMay 2, 2025, 5:02 PM

1 point

0 comments3 min readLW link

Recursive Cognitive Refinement (RCR): A Self-Correcting Approach for LLM Hallucinations

mxTheoFeb 22, 2025, 9:32 PM

0 points

0 comments2 min readLW link

The Checklist: What Succeeding at AI Safety Will Involve

Sam BowmanSep 3, 2024, 6:18 PM

142 points

49 comments22 min readLW link

(sleepinyourhat.github.io)

Human-AI Complementarity: A Goal for Amplified Oversight

rishubjain and Sophie Bridgers

Dec 24, 2024, 9:57 AM

27 points

4 comments1 min readLW link

(deepmindsafetyresearch.medium.com)

Will AI and Humanity Go to War?

Simon GoldsteinOct 1, 2024, 6:35 AM

9 points

4 comments6 min readLW link

I Recommend More Training Rationales

Gianluca CalcagniDec 31, 2024, 2:06 PM

2 points

0 comments6 min readLW link

Launching Applications for the Global AI Safety Fellowship 2025!

Aditya_SKNov 30, 2024, 2:02 PM

11 points

5 comments1 min readLW link

A Universal Prompt as a Safeguard Against AI Threats

Zhaiyk SultanMar 10, 2025, 2:28 AM

1 point

0 comments2 min readLW link

A Safer Path to AGI? Considering the Self-to-Processing Route as an Alternative to Processing-to-Self

opApr 21, 2025, 1:09 PM

1 point

0 comments1 min readLW link

Tetherware #1: The case for humanlike AI with free will

Jáchym FibírJan 30, 2025, 10:58 AM

5 points

14 comments10 min readLW link

(tetherware.substack.com)

Machine Unlearning in Large Language Models: A Comprehensive Survey with Empirical Insights from the Qwen 1.5 1.8B Model

Saketh BaddamFeb 1, 2025, 9:26 PM

9 points

2 comments11 min readLW link

AI Safety Oversights

Davey MorseFeb 8, 2025, 6:15 AM

3 points

0 comments1 min readLW link

Gradient Anatomy’s—Hallucination Robustness in Medical Q&A

DieSabFeb 12, 2025, 7:16 PM

2 points

0 comments10 min readLW link

OpenAI’s NSFW policy: user safety, harm reduction, and AI consent

8e9Feb 13, 2025, 1:59 PM

4 points

3 comments2 min readLW link

Out of the Box

jesseduffieldNov 13, 2023, 11:43 PM

5 points

1 comment7 min readLW link

Apply to the Conceptual Boundaries Workshop for AI Safety

ChipmonkNov 27, 2023, 9:04 PM

50 points

0 comments3 min readLW link

Public Opinion on AI Safety: AIMS 2023 and 2021 Summary

Jacy Reese Anthis, Janet Pauketat and Ali

Sep 25, 2023, 6:55 PM

3 points

2 comments3 min readLW link

(www.sentienceinstitute.org)

Title: IAM360: The Future of Human-AI Symbiosis — Can We Reach Investors?

Bruno Massena MassenaApr 29, 2025, 7:02 PM

1 point

0 comments1 min readLW link

Safety First: safety before full alignment. The deontic sufficiency hypothesis.

ChipmonkJan 3, 2024, 5:55 PM

48 points

3 comments3 min readLW link

Gaia Network: An Illustrated Primer

Rafael Kaufmann Nedal and Roman Leventov

Jan 18, 2024, 6:23 PM

3 points

2 comments15 min readLW link

No comments.