#llm
4 posts filed under “llm”
Building Better AI Evals: A Practical Guide to LLM Evaluation
How to create custom evaluations, model-graded assessments, and domain-specific benchmarks that actually predict real-world performance
Running Untrusted LLM Code Without Fear: The Implementation Guide
Last week, I shared how I built Fission, a high-performance sandbox for executing LLM-generated code using Firecracker microVMs.
Beyond Simple Prompts: Production-Grade LLM Techniques with DSpy
I've been watching startups achieve magical results with LLMs, and I noticed something: they're not using ChatGPT.
Running Untrusted LLM Code Without Fear: Building a MicroVM Sandbox
Every time an LLM generates code, you face a choice: trust it blindly or spend hours reviewing it. Neither option scales.