WHAT'S NEW
What's new
New lessons, designs, papers and practice rounds, newest first.
15 November 2026
- ConceptWhy LLM Apps Fail: The Three Gulfs · AI Engineering
- ConceptSimulated Users and Test Environments for Agents · AI Engineering
- ConceptSafety and Red-Team Evals: Jailbreaks, Injection and Tool Poisoning · AI Engineering
- ConceptReviewing Traces at Scale: Sampling, Clustering and Review Tools · AI Engineering
- ConceptRAG Evals: Retrieval, Faithfulness and Relevance · AI Engineering
- ConceptOnline Evals: Sampled Judges, Guardrails and User Signals · AI Engineering
- ConceptMulti-Turn Chat Evals: Sessions, Simulated Users and Drift · AI Engineering
- ConceptMulti-Agent Evals: Hand-offs, Roles and Verification · AI Engineering
- ConceptLabelling with a Team: Rubrics, Cohen's Kappa and Alignment · AI Engineering
- ConceptLLM Judges: Pairwise Preferences and Pass/Fail Checks · AI Engineering
- ConceptImproving with Evals: Cheapest Fix First, Then Cut Cost · AI Engineering
- ConceptImproving Tools with Evals: Held-Out Tasks and Transcripts · AI Engineering
- ConceptEvaluating an MCP Server: Tool Choice, Descriptions and Distractors · AI Engineering
- ConceptEvals in CI: Golden Sets, Regression Gates and Model Upgrades · AI Engineering
- ConceptError Analysis: From Traces to Failure Rates · AI Engineering
- DesignDesign an On-Call Engineering Copilot · System Design
- DesignDesign an Incident Investigation Agent · System Design
- DesignDesign a Trip Planner Agent · System Design
- DesignDesign a Shared Recommendation Foundation Model · System Design
- DesignDesign a Recruiting Assistant Agent · System Design
- DesignDesign a Codebase Q&A Assistant · System Design
- DesignDesign Support Answers from Past Tickets · System Design
- DesignDesign Short-Video Recommendations · System Design
- DesignDesign Recommendations for a New Category · System Design
- DesignDesign Job Recommendations · System Design
- ConceptCoding Agent Evals: Hidden Tests and Test Tampering · AI Engineering
- ConceptCode Checks First: Assertions, Schemas and Execution · AI Engineering
- ConceptChoosing the Right Eval: Ship Checks, Regression Tests, Monitors and Guardrails · AI Engineering
- ConceptCan You Trust Your Judge? TPR, TNR and Corrected Pass Rates · AI Engineering
- ConceptBuilding Your First Eval Set: Real Traces and Synthetic Queries · AI Engineering
- QuizApplied evals quiz · Practice
- InterviewApplied Evals Practice · AI Engineering
13 November 2026
- ConceptWhy Look Inside a Model? · AI Engineering
- ConceptValidating Interpretability Claims · AI Engineering
- PaperUnderstanding AI from the Inside · Papers Explained
- ConceptTranscoders and Attribution Graphs · AI Engineering
- ConceptThe Residual Stream and Circuits · AI Engineering
- ConceptSteering Vectors · AI Engineering
- ConceptSparse Autoencoders · AI Engineering
- ConceptSAE Failures and Alternatives · AI Engineering
- ConceptProbing Classifiers · AI Engineering
- ConceptModel Diffing · AI Engineering
- ConceptLogit Lens, Tuned Lens and Verbalisers · AI Engineering
- ConceptLinear Representations and Universality · AI Engineering
- ConceptKnowledge Localisation and Editing · AI Engineering
- ConceptInterpretability for AI Safety · AI Engineering
- InterviewInterpretability Scenarios · AI Engineering
- ConceptFeatures, Polysemanticity and Superposition · AI Engineering
- ConceptActivation Patching and Circuit Discovery · AI Engineering
- InterviewAI Interpretability Practice · AI Engineering
12 November 2026
- FeatureMy progress pageSee lessons done per track and roadmap, your study streak, and the quiz and mock answers you've opened. Download your progress to move it to another device.