Notes on ForecastBench
ForecastBench continuously evaluates the performance of LLMs against an automatically generated, continuously updated set of forecasting questions.
ForecastBench continuously evaluates the performance of LLMs against an automatically generated, continuously updated set of forecasting questions.
Practical guidelines on context engineering, like having an append-only context, using response prefill to remove/force tools, setting up restorable compression strategies, and more.
Notes as I learn about WebAssembly by building an open source project.
Semi-ordered thoughts on the new Digital Personal Data Protection Bill by the Indian Government.
A note on the role of communities in open source.