▶ Videos →

📰 Dev.to · AS

2 articles · Updated every 3 hours · View all reads

All Articles 180,933 Blog Posts 165,067 Tech Tutorials 48,404 Research Papers 35,698 News 22,584 ⚡ AI Lessons

Kmemo 2.0 is out, and the two gaps I admitted to in the first post are closed

Dev.to · AS 🧠 Large Language Models ⚡ AI Lesson 1mo ago

Kmemo 2.0 is out, and the two gaps I admitted to in the first post are closed

A follow-up to the Kmemo write-up: the verifier's catch rate, the GPTCache comparison, the guard a commenter asked for, and a core that no longer needs the JVM.

Kmemo: a semantic cache for LLM calls that refuses to serve you the wrong answer

Dev.to · AS 🧠 Large Language Models ⚡ AI Lesson 1mo ago

Kmemo: a semantic cache for LLM calls that refuses to serve you the wrong answer

Semantic caching cuts LLM cost and latency, and it will happily hand back the answer to a question nobody asked. Kmemo treats that failure as the main problem r