# Kabir Khandpur

Kabir's blog with posts on various topics.

## Posts

- [SWE-bench Multilingual](https://kabirk.com/multilingual.md): Introducing a new dataset in the SWE-bench family with 300 curated tasks in 9 programming languages to evaluate LLMs on software engineering tasks.
- [How well can LLMs see?](https://kabirk.com/wimmelbench.md): Creating a small benchmark to test how well multimodal language models can find specific objects in complex Where's Waldo-style illustrations.
- [Using the checker idiom to monitor software systems](https://kabirk.com/checker.md): Exploring a missing piece of the software observability stack to monitor business logic.
- [Making Quartz site rebuilds 25x faster](https://kabirk.com/rebuilds.md): Implementing partial builds to reduce the time taken to live reload a static site by >99%.
- [Notes on Britain's finances](https://kabirk.com/ukfinances.md): A look into how the UK government raises and spends money.
- [Why is Singapore's public transport so good?](https://kabirk.com/sgtransport.md)