Glean CEO Arvind Jain explains why model routing helps control AI costs for organizations, and how human feedback loops at scale improve its routing systems.
Setting type
Claude Computing
Pulling labs, repos, and the catch-up path…
Harnesses, graphs, loops, APIs you call this week — tagged with Ng’s application skills. Not a training desk. New here is the decoder. Starting a project this week? Catch up is the four-skill map — not more news.
No splash for ML foundations. The lanes below still scan.
Cookbooks for building AI apps: context, harness, graphs, cloud.
No ML foundations headlines in this lane.
Harness, loops, graphs, MCP, permissions, evals as acceptance.
No ML foundations headlines in this lane.
Clone-to-ship: RAG, eval harnesses, agent wrappers. Not train-a-model.
No ML foundations headlines in this lane.
Watchlist posts for people building AI apps. Originals, not architecture notes.
Glean CEO Arvind Jain explains why model routing helps control AI costs for organizations, and how human feedback loops at scale improve its routing systems.
Latent Space11d agoLive
Models keep absorbing the harness into their weights — soon, it will be a harness for human attention rather than for the model.
Latent Space8d agoLive