Topic
Snowflake
2 episodes
-
Snowflake CEO finds GLM 5.2 competitive with Opus 4.7 at a fraction of the cost
Cooper and Miles dig into Snowflake's claim that GLM-5.2 can hang with Claude Opus 4.7 on a real coding benchmark for much less money, and why the interesting part is not 'GLM wins' but 'cheap models are getting close enough that harness quality and retry policy start to matter more than leaderboard prestige.'
-
How query logs fix AI agent SQL errors
Justy and Cody dig into DataHub's new Context Intelligence layer, which mines SQL query logs to build a semantic index for AI agents. They unpack why raw schema fails at scale, whether query history actually solves the hallucination problem, and who should care about this in practice.