Takes on “Alignment Faking in Large Language Models”
Large Hadron Collider regularly makes magic
Large language overkill: How SLMs can beat their bigger, resource-intensive cousins
Alignment faking in large language models \ Anthropic
Beyond LLMs: How SandboxAQ’s large quantitative models could optimize enterprise AI
Deploying Large Language Models on Kubernetes
Black-box forgetting: A new method for tailoring large AI models