LLM Evaluation

5 pieces on LLM Evaluation.

News & Analysis

news
Shan2026-09-12
BenchmarksAI AgentsByteDanceLLM EvaluationCode Generation

ByteDance's HarnessDev: Only 34 of 64 LLM Harness Changes Generalize

HarnessDev benchmarks the harness LLMs build, not the answers they return. Execution feedback matched held-out results only 53.1% of the time.

Read more
news
Shan2026-09-07
Agentic AIMulti-Agent SystemsProduction MLPythonLLM Evaluation

40% of Production AI Failures Are Silent: Fix With a Watchdog

Datadog data shows 40% of production AI failures return HTTP 200. A lightweight 1B-parameter watchdog at each handoff seam catches what output-level eval cannot.

Read more
news
Shan2026-08-29
Agentic AIHuman-in-the-LoopLLM ApplicationsSystems EngineeringLLM Evaluation

Risk-Scored Routing Cuts Human Review to High-Signal Queries Only

A text-to-SQL team replaced blanket approval gates with a four-signal risk router, sending only genuinely ambiguous actions to human reviewers.

Read more
news
Shan2026-08-20
LLM EvaluationAgentic WorkflowsLLMOpsPrompt EngineeringProduction AI

LLM Judge Approved Its Own Errors: Three Biases Explained

A production SQL pipeline approved wrong queries for weeks. The judge and generator shared the same model — and that structural flaw caused the incident.

Read more
Articles
Shan2026-06-10
Prompt EngineeringDSPyLLM EvaluationProduction AILLMOps

Stop Hand-Tuning Prompts: A Production Workflow for Automated LLM Optimization

Move beyond trial-and-error prompting with a measurable workflow for evaluating and optimizing LLM prompts in production systems.

Read more