In this video, I discuss interesting features found in other languages that English could benefit from, including time-independence, clusivity, absolute direction, and evidentiality.

Sparse Autoencoders (SAEs) have recently gained attention as a means to improve the interpretability and steerability of Large Language Models (LLMs), both of which are essential for AI safety. In ...

Say goodbye to source maps and compilation delays. By treating types as whitespace, modern runtimes are unlocking a “no-build” TypeScript that keeps stack traces accurate and workflows clean.

Artificial intelligence and its promise to revolutionize programming—and possibly overthrow human sovereignty—is a central story of the post-Covid world. But for JavaScript developers, it is only one ...

Abstract: Open-vocabulary querying in 3D space is challenging but essential for scene understanding tasks such as object localization and segmentation. Language embedded scene representations have ...

Abstract: Large Language Models (LLMs) have been widely used in software development, yet the security of AI-generated code remains a critical concern. This research examines security vulnerabilities ...