2026

• 09 Apr Bayesian DL & UQ Part 7: The Future of UQ — Uncertainty in the Age of Foundation Models
• 09 Apr Bayesian DL & UQ Part 6: UQ in Science — Molecules, Proteins, and Materials
• 09 Apr Bayesian DL & UQ Part 5: Single-Pass UQ — Evidential Deep Learning and Distance-Aware Methods
• 09 Apr Bayesian DL & UQ Part 4: Calibration and Conformal Prediction
• 09 Apr Bayesian DL & UQ Part 3: The Anatomy of Uncertainty — Aleatoric vs. Epistemic
• 09 Apr Bayesian DL & UQ Part 2: The Art of Approximation — From Variational to Ensemble
• 09 Apr Bayesian DL & UQ Part 1: The Language of Bayesian Inference
• 09 Apr Bayesian DL & UQ Part 0: Beyond Predictions — Why Uncertainty Matters
• 08 Apr Code Quality for Beginners Part 4: Encode Your Standards — CLAUDE.md, Harness Engineering, and the Full Setup
• 08 Apr Code Quality for Beginners Part 3: Collaborate Like a Pro — Git Workflow, Code Review, and Dependency Safety
• 08 Apr Code Quality for Beginners Part 2: Test and Automate — From pytest to CI/CD Pipelines
• 08 Apr Code Quality for Beginners Part 1: Write Clean Code Before You Push — Formatting, Linting, and Data Validation
• 06 Apr Agent Tool Interfaces Part 2: Orchestrating Tool Interfaces — From Harness Design to GraphRAG
• 06 Apr Agent Tool Interfaces Part 1: How Agents Connect to Tools — The Complete Interface Landscape
• 06 Apr Causal Inference Part 7: The Causal Inference Agent — When LLMs Meet Causality
• 06 Apr Causal Inference Part 6: End-to-End Practice — The Causal Pipeline in Code
• 06 Apr Causal Inference Part 5: Beyond the Average — Heterogeneous Effects and Causal Discovery
• 06 Apr Causal Inference Part 4: Estimation — From Estimand to Estimate
• 06 Apr Causal Inference Part 3: Identification — From Design to Estimand
• 06 Apr Causal Inference Part 2: Graphs and Interventions — Structural Causal Models
• 06 Apr Causal Inference Part 1: The Language of Causation — Potential Outcomes
• 06 Apr Causal Inference Part 0: Beyond Correlation — Why Causal Inference?
• 06 Apr oh-my-* — When One AI Agent Isn't Enough, Build a Team
• 06 Apr Harness Engineering Part 3: In Practice — Tools, Patterns, and Starting Points
• 06 Apr Harness Engineering Part 2: Self-Improving Harnesses — Lessons from Meta-Harness Research
• 06 Apr Harness Engineering Part 1: Why It Matters — The Shift Beyond Prompts and Context
• 04 Apr Synthesis AI Part 5: From Algorithm to Lab — CRO Integration and the Remaining Gap
• 04 Apr Synthesis AI Part 4: Synthesis-Aware Design — Making AI-Generated Molecules Makeable
• 04 Apr Synthesis AI Part 3: Retrosynthesis — Can AI Plan How to Make a Molecule?
• 04 Apr Synthesis AI Part 2: Reaction Prediction — Can AI Predict What Chemistry Will Do?
• 04 Apr Synthesis AI Part 1: The Synthesis Bottleneck — Why "Make" Lags Behind
• 03 Apr How Karpathy Turned an LLM into a Self-Improving Research Wiki — And Why RAG Wasn't Needed
• 03 Apr Building an AI-Native Organization: From Copilots to Company Intelligence
• 31 Mar SSL for Co-Folding Part 4: The Road Ahead — Data Flywheels, Foundation Models, and Open Questions
• 31 Mar SSL for Co-Folding Part 3: Untapped Opportunities and the Confidence Calibration Trap
• 31 Mar SSL for Co-Folding Part 2: How Co-Folding Models Use Synthetic Data — An SSL Perspective
• 31 Mar SSL for Co-Folding Part 1: The Semi-Supervised Revolution in Computer Vision
• 22 Mar Impact of AI on Scientific Knowledge Production — Part 3: Empirical Evidence from AlphaFold and Open Questions
• 22 Mar Impact of AI on Scientific Knowledge Production — Part 2: Beyond the Productivity Debate — How AI Distorts Research Direction
• 22 Mar Impact of AI on Scientific Knowledge Production — Part 1: Three Theoretical Frameworks
• 18 Mar From Millions to Billions — and Back: Ultra-Large Virtual Screening and the Case for Bespoke Libraries
• 18 Mar Toward Accelerating the Entire Design–Make–Test Cycle with AI
• 18 Mar Case Study — Coming Soon
• 18 Mar Protein Design — Coming Soon
• 17 Mar From OpenClaw to NemoClaw: The Technical Landscape of the Claw AI Agent Ecosystem
• 17 Mar Protein AI Series Part 9: Where Is the Field Heading?
• 17 Mar Protein AI Series Part 8: The Data Landscape
• 17 Mar Protein AI Series Part 7: Training Engineering and Scaling
• 17 Mar Protein AI Series Part 6: The Conformational Diversity Problem
• 17 Mar Protein AI Series Part 5: Four Design Strategies Compared
• 17 Mar Protein AI Series Part 4: Co-Folding and the Open-Source Race
• 17 Mar Protein AI Series Part 3: IPA → Diffusion → Flow Matching
• 17 Mar Protein AI Series Part 2: Evoformer → Pairformer → Pairmixer
• 17 Mar Protein AI Series Part 1: MSA vs PLM vs Hybrid
• 17 Mar Protein AI Series Part 0: What Is Protein Structure Prediction?
• 10 Mar Geometric Deep Learning for Molecules
• 10 Mar AI-Biotech Investment Landscape
• 10 Mar Lessons from Being Employee Number One