Read news on alignment with our app.
Read more in the app
Center for the Alignment of AI Alignment Centers
This researcher turned OpenAI’s open weights model gpt-oss-20b into a non-reasoning ‘base’ model with less alignment, more freedom
Data everywhere, alignment nowhere: What dashboards are getting wrong, and why you need a data product manager
LLM's Illusion of Alignment
Extreme Super-Resolution via Scale Autoregression and Preference Alignment
Alignment is not free: How model upgrades can silence your confidence signals
Alignment faking in large language models
Takes on "Alignment Faking in Large Language Models"
Productivity Versus Alignment
StarCoder2-Instruct: Transparent Self-Alignment for Code Generation
