--- title: "Stop Making Models Bigger, Make Them Behave — Kobie Crawdord, Snorkel" url: https://daily.dev/posts/stop-making-models-bigger-make-them-behave-kobie-crawdord-snorkel-ixkywff1q source_url: https://www.youtube.com/watch?v=TNwJ1LMiENk type: video:youtube source: "AI Engineer" published: 2026-06-10T17:17:55.465Z updated: 2026-06-10T17:18:15.852Z tags: ["reinforcement-learning", "data-quality"] reading_time: 20 upvotes: 0 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Stop Making Models Bigger, Make Them Behave — Kobie Crawdord, Snorkel **[AI Engineer](https://daily.dev/sources/aidotengineer)** · 20 min read · 0 upvotes · 0 comments ## Summary A conference talk from Snorkel's developer advocate presenting research showing a 4-billion parameter model can outperform a 235-billion parameter model on financial analysis tool-use tasks. Using GRPO-based reinforcement learning with a high-quality expert-curated dataset, the team achieved roughly double the pass@1 performance at under $500 per training run. The key insight: the larger model failed not due to reasoning deficits but due to poor tool-use discipline — it queried non-existent tables and hallucinated answers. The fine-tuned smaller model learned to first discover available tables, inspect schemas, and self-correct errors. Surprisingly, training on single-table examples only yielded the best results, and the improvement generalized to harder multi-table benchmarks as well. The takeaway is that identifying the specific behavioral failure mode and targeting it with the right data is often more effective than scaling up model size. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [How Can A Model 10,000× Smaller Outsmart ChatGPT?](https://daily.dev/posts/how-can-a-model-10-000-smaller-outsmart-chatgpt--rgks7qbfm) · Towards Data Science · 9 upvotes · 0 comments --- Tags: [#reinforcement-learning](https://daily.dev/tags/reinforcement-learning), [#data-quality](https://daily.dev/tags/data-quality) [View this post on daily.dev](https://daily.dev/posts/stop-making-models-bigger-make-them-behave-kobie-crawdord-snorkel-ixkywff1q)