Alignment will happen by default. What’s next? — LessWrong

I’m not 100% convinced of this, but I’m fairly convinced, more and more so over time. I’m hoping to start a vigorous but civilized debate. I invite y…

x Alignment will happen by default. What’s next? — LessWrong AI Frontpage 2025 Top Fifty: 7 % 98 Alignment will happen by default. What’s next? by Adrià Garriga-alonso 25th Nov 2025 AI Alignment Forum Linkpost for open.substack.com 7 min read 133 98 Ω 25 I’m not 100% convinced of this, but I’m fairly convinced, more and more so over time. I’m hoping to start a vigorous but civilized debate. I invite you to attack my weak points and/or present counter-evidence. My thesis is that intent-alignment is basically happening, based on evidence from the alignment research in the LLM era. Introduction T

related reading

• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• Alignment is not solved but it increasingly looks solvablealigned.substack.com
• Current AIs seem pretty misaligned to me — LessWronglesswrong.com
• Deep Deceptiveness — LessWronglesswrong.com
• The Artificiality of Alignmentjoinreboot.org
• Self-Fulfilling Misalignment Data Might Be Poisoning Our AI Modelsturntrout.com
• The Case Against AI Control Research — LessWronglesswrong.com
• Alignment By Default — AI Alignment Forumalignmentforum.org
• Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment — LessWronglesswrong.com
• The Machines Lack Honour — LessWronglesswrong.com
• Many arguments for AI x-risk are wrong — AI Alignment Forumalignmentforum.org
• The case against AI alignment — LessWronglesswrong.com