Evaluation

Recommended Posts

• Why Embeddings Cannot Solve Eval-Set Contamination

  29 Jun, 2026 · 11 min read

  A technical deep dive on why semantic embedding search is useful but insufficient for eval-set decontamination: leakage is about evaluation advantage, not just text similarity.

• Pretraining Contamination: Why Don't Train on the Test Set Became Hard

  29 Jun, 2026 · 14 min read

  A practical introduction to LLM pretraining contamination: why benchmark leakage is not ordinary deduplication, how public evals leak into web-scale corpora, and how layered decontamination pipelines reduce risk.

• How to Arbitrarily Increase the Difficulty of Agent Evaluation Sets

  28 May, 2026 · 18 min read

  A practical framework for making agent benchmarks harder in a controlled way: treat difficulty as trajectory-graph complexity, not prompt wording. Covers deterministic scoring, capability facets, harness effects, and systematic data generation.

• The Mercor Breach: What 4TB of Stolen Data Reveals About How Frontier AI Labs Actually Train Models

  12 Apr, 2026 · 22 min read

  A $10B AI data vendor was breached, exposing 84 Airtable workspaces of training data for OpenAI, Anthropic, Apple, Amazon, and Meta. This post analyzes what the public reporting reveals about each lab's evaluation methodology — rubric design, RLHF pipelines, and quality control — and what it means for the industry.

• The Unverifiable Reward Problem: The Real Frontier of RL for LLMs

  7 Mar, 2026 · 11 min read

  Deep research on tasks with unverifiable rewards in RL — the key bottleneck for scaling RL beyond math and code. Covers JEPO, NRT, RLNVR, self-play methods, GenRM, Constitutional AI, reward hacking mitigation, and more.

• Instruction Following: What Models Get Wrong and How to Fix It with Better Post-Training Data

  4 Mar, 2026 · 36 min read

  LLMs can write poetry and solve math, but ask them to 'respond in exactly 3 bullet points using only lowercase' and they stumble. This post dissects the taxonomy of instruction-following failures and provides a practical playbook for building post-training data that actually fixes them.

• Adding Ads in LLM/Chatbot: Character Training for Monetization

  1 Jan, 2026 · 4 min read

  Exploring how to integrate ads in LLMs through character training—making recommendations genuinely helpful rather than annoyingly promotional.

• Post-Training Is Not 'One Algorithm': Objective Functions and Implementation Essentials for PPO / DPO / GRPO

  30 Dec, 2025 · 12 min read

  Reading notes on RLHF covering PPO, DPO, and GRPO—understanding post-training as an engineering pipeline rather than a single algorithm.

• RLHF from an Engineering Perspective: PPO, GRPO, DPO, and Tool-Use Implementation

  30 Dec, 2025 · 12 min read

  A practical engineering guide to RLHF implementation—covering PPO, GRPO, DPO, and tool-use training with code snippets and debugging tips.