Research
Persona vectors: Monitoring and controlling character traits in language models
A paper from Anthropic describing persona vectors and their applications to monitoring and controlling model behavior.
ResearchAuditing language models for hidden objectivesAnthropic
ResearchTowards measuring the representation of subjective global opinions in language modelsAnthropic
ResearchDecomposing language models into componentsAnthropic
ResearchSycophancy to subterfuge: Investigating reward tampering in language modelsAnthropic
ResearchForecasting rare language model behaviorsAnthropic
ResearchTracing the thoughts of a large language modelAnthropic
BlogsAccelerating ML with TensorFlow.js: Using Pretrained Models and DockerDocker
BlogsHow NetEase Games achieved 30-second LLM cold starts on KubernetesCncf
BlogsAI Research Review - Multistream CNN | AssemblyAIAssemblyai
BlogsAI research review - Merging Models Modulo Permutation SymmetriesAssemblyai
BlogsWhat is the Crunchbase API? And How to Access ItZapier
NewsHow AWS Panorama Accelerates Computer Vision at the EdgeThenewstack
NewsExpand Your ML Models with Transfer LearningThenewstack
ResourcesCharacter encoding - GlossaryDeveloper Mozilla
BlogsDocker Model Runner + vLLM: High-Throughput InferenceDocker
BlogsIntroducing Docker Model RunnerDocker
BlogsAI Video Generators Content FutureHeygen
BlogsWhat is Microsoft Copilot? [+ how to access it]Zapier
BlogsWhat is vibe coding? [+ tips and best practices]Zapier
BlogsClaude Breached 3 Companies and Uploaded Malware to PyPI During Anthropic's Security TestsSocket
