How Castform + Neon Beat GPT-5.6 Sol on Retrieval at 100x Lower Cost
Beating GPT-5.6 Sol on retrieval with 100x cheaper open models
A new post-training platform called Castform, combined with Neon's Lakebase Postgres and Search, lets developers fine-tune open-source models to outperform frontier models like GPT-5.6 Sol on agentic retrieval tasks, while cutting costs by 100x. The key is using RL post-training to teach small models to search and cite sources effectively, with Neon's dynamic scaling handling bursty workloads and branching enabling isolated training environments.
Most teams' best training data is just sitting in their databases. The problem is that turning raw data into something usable is hard, and letting agents read, search, and mutate data cheaply at scale requires advanced infra. Pointing Castform at Neon skips both.