AI Alignment Is Censorship - by Kerem Goksel and mona
joinreboot.org · 2,659 words · saved by 1 readers
On LLMs, content control, and hegemony
It seems trite to say that we are living in turbulent times. The flame of American unipolar hegemony is flickering, there is massive geopolitical instability and economic volatility, and the rate of technological progress continues to accelerate. As these crises intensify and are magnified by technology, it’s critical to be clear-eyed about the disconnects between rhetoric and reality, particularly when it comes to the conceptual monolith of “AI alignment.” This week, Mona Wang and Kerem Göksel break down how alignment is discussed, how it’s deployed, and make a compelling case that…
related reading
- Uncensored Modelserichartford.com
- Alignment is not solved but it increasingly looks solvablealigned.substack.com
- Legilimens: Practical and Unified Content Moderation forLarge Language Model Servicesarxiv.org
- Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignmentalignmentpretraining.ai
- Off Target | CNAScnas.org
- Spring 2026 Projects - SPARsparai.org
- [2502.17424] Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMsarxiv.org
- Refusal in LLMs is mediated by a single direction — LessWronglesswrong.com
- What is input/output filtering in AI safety?blog.bluedot.org
- Uncensor any LLM with abliterationhuggingface.co
- Agentic Misalignment: How LLMs Could be Insider Threats — LessWronglesswrong.com
- RigorLLM: Resilient Guardrails for Large Language Models against Undesired Contentarxiv.org