Many arguments for AI x-risk are wrong — LessWrong
lesswrong.com · 15,325 words · saved by 1 readers
The following is a lightly edited version of a memo I wrote for a retreat. It was inspired by a draft of Counting arguments provide no evidence for A…
x Many arguments for AI x-risk are wrong — LessWrong Deceptive Alignment AI Risk Skepticism AI Governance Counting arguments Language Models (LLMs) AI Community Frontpage 182 Many arguments for AI x-risk are wrong by TurnTrout 5th Mar 2024 AI Alignment Forum 15 min read 96 182 Ω 48 The following is a lightly edited version of a memo I wrote for a retreat. It was inspired by a draft of Counting arguments provide no evidence for AI doom . I think that my post covers important points not made by the published version of that post. I'm also thankful for the dozens of interesting conversations and
related reading
- Many arguments for AI x-risk are wrong — AI Alignment Forumalignmentforum.org
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- The Case Against AI Control Research — LessWronglesswrong.com
- Deep Deceptiveness — LessWronglesswrong.com
- Where I agree and disagree with Eliezer — LessWronglesswrong.com
- Current AIs seem pretty misaligned to me — LessWronglesswrong.com
- Thoughts on the impact of RLHF research — LessWronglesswrong.com
- Self-Fulfilling Misalignment Data Might Be Poisoning Our AI Modelsturntrout.com
- Should We Train Against (CoT) Monitors? — LessWronglesswrong.com
- Thoughts on the conservative assumptions in AI controlblog.redwoodresearch.org
- Alignment will happen by default. What’s next? — LessWronglesswrong.com