✨ Kyle Wild ✨

Reading

OpenAI: Introducing study mode

by Simon Willison: July 29, 2025 (bookmarked )

OpenAI's new ChatGPT study mode showcases how carefully crafted system prompts can create entirely new platform features - emphasizing collaborative guidance over doing work for learners.

Context Rot: How Increasing Input Tokens Impacts LLM Performance

by Kelly Hong, Anton Troynikov, Jeff Huber (Chroma): July 14, 2025 (bookmarked )

Fascinating research revealing how LLMs' performance degrades non-uniformly as context length increases - models perform better with randomly shuffled text than logically structured content, suggesting our current evaluation methods miss critical reliability issues.

Writing Code Was Never The Bottleneck

by Pedro: June 30, 2025 (bookmarked )

arguing that understanding, collaboration, and careful review remain the true bottlenecks in software development, not code generation

Tools: Code Is All You Need

by Armin Ronacher: July 03, 2025 (bookmarked )

Been saying this for a while, but not as eloquently.

View all reading →

Writing

The Rise and Fall of "Vibe Coding"

If you played around with Cursor and Sonnet 3.5 a few months ago and found it lacking, join the crowd – but don't get attached to your conclusions.

View all writing →