The ML Blog

Deep dives and interview guides to help you ace your next role.

Agent Engineering

Laguna S 2.1: How Poolside Built the Best 118B Agentic Coding Model

Poolside's Laguna S 2.1 is a 118B MoE model that scores 70.2% on Terminal-Bench 2.1 - beating models ten times its size. Here is what changed under the hood.

Jul 22, 20268 min read
Machine Learning

The Architecture Behind Kimi K3: Open 3T-Class Intelligence

Kimi K3 scales to 2.8T parameters using Kimi Delta Attention and Stable LatentMoE. Discover how this open model achieves a 1M token context window and 2.5x scaling efficiency.

Jul 20, 20265 min read
Machine Learning

Understanding Kronos: How a Foundation Model Reads the Language of Financial Markets

Generic Time Series Foundation Models fail on financial data. Kronos fixes this by treating K-line data as a discrete language. A stage-by-stage breakdown of its architecture, from BSQ tokenization to detokenization.

Jun 5, 202612 min read
Machine Learning

The Brutal Truth About ML Trading: Why Your XGBoost Model Keeps Failing (And What Actually Works)

We built the "perfect" XGBoost trading model — walk-forward validation, 26 features, intraday data. Result: 50.2% accuracy, Sharpe 0.18, 0 trades. Every failure documented, and what the DRW Kaggle 1st place winner did instead.

Jun 5, 202618 min read
Interviews

The Complete ML Interview Guide 2026: Topics, Tips & Mock Tests

A complete machine learning interview guide for 2026 requires mastering system design, fundamental algorithms, and modern deep learning frameworks.

May 25, 20266 min read
LLMs

Trainer vs SFTTrainer: The Complete LLM Training Stack for Financial Services

How Hedge Funds and Quant Teams Navigate 15+ Training Libraries to Build Custom AI Models

May 21, 20267 min read