Signals

Stripe enters the blockchain space with Tempo, an L1 blockchain focused on stablecoin utility for real-world business applications.

Key insights on building robust evaluation systems that enable rapid model updates and continuous improvement in AI applications.

A foundational AI research insight: general computational methods ultimately outperform human knowledge-based approaches.

Discussion on how complex algorithmic problems can be simplified using constraint solvers, and the trade-offs between custom solutions and dependency management.

A practical guide demonstrating how economists can build sophisticated AI agents for autonomous research tasks using modern frameworks like LangGraph.

A general audience introduction to how large language models like ChatGPT are built, from data collection to neural network training.

Step-by-step tutorial on building character-level language models, starting with simple bigram models and progressing to transformer architectures.

A systematic approach to collaborating with AI systems on software projects, addressing code bloat, architectural drift, and context dilution through structured constraints and validation checkpoints.

How physics training in linear algebra, tensor calculus, and entropy provides the mathematical foundation for understanding LLMs.

A unifying framework for defeasible reasoning in disjunctive logic programs under answer set semantics using argumentation rules.