Inception's Mercury Coder separates proposing a code change from inserting it into a complete file. A coding assistant may return a changed fragment surrounded by comments saying that other code remains unchanged. Mercury's Apply-Edit endpoint takes that fragment alongside the original file and is designed to return the merged file while preserving surrounding structure, comments and indentation. This gives coding tools a dedicated step for turning suggested changes into usable file contents. The product announcement documents the input format and endpoint.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
postInception ships Mercury Decide update with ZDR and 66k context
postInception launches Mercury Voice, a diffusion LLM for low-latency voice agents
postToday, we’re introducing Mercury 2.5, the most capable diffusion LLM on the…
postInception ships Mercury 2.5 Preview at roughly 1,100 tokens per second