True Positive Weekly #144

The most important artificial intelligence and machine learning news and articles

Hey, in this issue: making sense of memory in AI agents; a tutorial on building an AI agent; a new suite of open translation models; a new ML paradigm for continual learning; a visual introduction to dimensionality reduction; continuous batching for efficient LLM serving explained; and more.

• Making sense of memory in AI agents

• The continual learning problem

• [Explained] Continuous batching for efficient LLM serving

• [Model] TranslateGemma: A new suite of open translation models

• [Tutorial] Build your first AI agent with Gemini, n8n and Google Cloud Run

• [Google] Nested Learning: A new ML paradigm for continual learning

• A visual introduction to dimensionality reduction with Isomap

• How do language models solve Bayesian network inference?

This is it for this week. Please like, comment, share, or become a paid subscriber to support my work.