Red Planet Labs

Red Planet Labs reports that large language models (LLMs) are now consistently one-shotting complex backend challenges, including an unbalanced social graph, a social graph with fanout, and a Slack-li…

Red Planet Labs reports progress in teaching LLMs to one-shot complex backends at scale, achieving consistent one-shot generation of the fanout challenge—a core Twitter-like service—using Fable and Op…

A recent study found that large language models achieve only 33% success on full test suites for simple CRUD applications when realistic structural constraints are imposed, with most failures occurrin…