Topic
Llama 3
3 episodes
-
Implementing Prompt Compression to Reduce Agentic Loop Costs MachineLearningMastery
Justy and Cody kick around whether prompt compression is actually a smart production habit or just another neat demo. Cody starts skeptical about summary drift and hidden complexity, then they get concrete on why long agent loops get expensive fast, what the article's Python example is really proving, and where compressed history plus distilled instructions make sense right now.
-
Four Agent Orchestration Patterns
Justy and Cody dig into a benchmark study testing four multi-agent orchestration patterns across 10,000 SEC filings — sequential pipeline, parallel fan-out, hierarchical supervisor-worker, and reflexive self-correcting loop — unpacking the real cost-accuracy-scale trade-offs and how to pick the right one for production.
-
Benchmarking Multi Agent LLM Architectures for Financial Document Processing: A Comparative Study of Orchestration Patterns, Cost Accuracy Tradeoffs and Production Scaling Strategies
Justy and Cody break down a benchmark of four multi-agent LLM orchestration patterns for extracting structured data from SEC filings, focusing on cost, accuracy, latency, and what’s actually shippable in production. They compare sequential, parallel, hierarchical, and reflexive setups across 10,000 filings and land on a practical middle ground: hierarchical orchestration gets close to the best accuracy without the reflexive loop’s big cost hit.