Tag
This article is an engineering note that re-examines the design of coding agents from first principles, questions the impact of KV cache on current architectures, and proposes new methods for context management and decision-making.
Engineering notes on optimizing frame selection for feeding video to LLMs, covering scene detection, deduplication strategies, and token budget management.
Cursor's engineering notes reveal that agent failures often stem from the harness (scaffolding) rather than the model itself, with different tool formats across providers causing silent errors and reliability issues.
Wink Engineering evaluates the efficacy of neural super-resolution as a pre-filter for license plate OCR, concluding that it fails to improve accuracy and often leads to hallucinated characters compared to training directly on low-resolution data.