Stop Fine-Tuning to Fix Retrieval Problems — Anant Srivastava

Gives a diagnostic for choosing between prompt edits, retrieval and fine-tuning. It explains why fine-tuning to fix retrieval problems backfires.

• fine-tuning — Taking a trained model and training it a bit more on your own examples so it gets better at one specific job.

• videoDashboards Are Dead — Sarah Simionescu, Composio
• videoWe Built an AI Support Agent That Resolves 80% of Tickets — AssemblyAI
• videoWhat Makes Open Models Fast in Production — Sujee Maniyam, Nebius
• videoAn Interaction Is All You Need — Ivan Leo, Google DeepMind

• videoNo Memory, No Harness: Why the Database Is the Last Line of Defense — Kay Malcolm, OracleAI Engineer
• videoThe Half Life of Agent Infrastructure — Ben Kus, BoxAI Engineer
• videoYour Fine-Tuned Model Is Tech Debt: A 50x ROI House of Cards — Dan Bjornn, Lease EndAI Engineer

Checking sign-in…

Loading comments…