All Documents
3,528 documents available
Decision Trees
Explains decision tree concepts: entropy, information gain, ID3 algorithm, overfitting, and handling continuous or many-valued attributes.
Annotating documents
Guides human annotators through labeling entity mentions, relations, and coreferences in Watson Knowledge Studio using the ground truth editor.
CVPR 2017 Abstracts Collection
Lists CVPR 2017 paper titles, authors, abstracts, and comments for fast browsing of the conference proceedings.
Adding Recognizers
Explains how to create and register PII recognizers that extend SovereignGuard's detection capabilities before tokenization.
Writing Effective Skills
Distills patterns from production agent skills across multiple frameworks into actionable design principles for writing skills that agents actually follow.
Writing Guide
Defines a personal writing voice and style guide based on existing blog posts, with tone rules, structural patterns, and anti-patterns.
📘 Comprehensive Prompt-Writing Best Practices
Teaches 19 prompt-writing principles including the RTCF framework, with examples and common mistakes to avoid.
Sprint 3 Completion Report: LLM Egress Guard
Reports completion of Sprint 3 for an LLM egress guard, detailing context-aware parsing and false positive reduction for educational content.
FINAL QUALITY UPGRADES - EXTREMELY DETAILED RESPONSES
Forces three fusion strategies to produce 400-600 word summaries and 200-300 word answers by injecting aggressive word-count minimums and structured requirements into LLM prompts.
Paragraph Classification (Previous to KTM 10.4)
Explains how to detect, classify, and train paragraph-level classification in Kofax Transformation before version 10.4 made it a built-in feature.
Example - computing context-aware co-occurrence scores with CoCoScore
Walks through using CoCoScore to compute context-aware co-occurrence scores for disease-gene pairs from sentence-level co-mentions.
Retrieval & Prompts
Explains how CharMemory's extraction prompt and Vector Storage settings determine memory retrieval quality in SillyTavern.
07-ChapterML
Introduces machine learning concepts and methods for social scientists, covering the end-to-end ML process from problem formulation to deployment.
Paragraph Classification
Explains how to detect, classify, and train paragraph-level classification in Kofax Transformation Modules 10.4 using scripts and validation.
AGENTS
Documents the two current TUI apps, headless loop, file paths, key bindings, and recent release history for an agent project.
Loss Functions
Documents five loss functions for training energy-based models, with code examples and guidance on choosing between them.
Generic pipeline
Describes the Generic Pipeline for declarative deep learning experiments using YAML, covering installation, project structure, training, and customisation.
agent-CLAUDE
Defines the identity, workspace layout, sync rules, and behavioral constraints for a long-lived Claude Code session acting as a company knowledge agent.
Deep Learning for AI
Summarises a survey paper on deep learning origins, breakthroughs, and future challenges for AI researchers.
Writing Effective .clinerules
Defines best practices for writing.clinerules files that guide Cline's behavior, knowledge, and workflows.
Private Advertising Technology Working Group / Community Group Minutes - 2025-06 Meeting
Records discussion and decisions from a W3C working group meeting on global safety limits and per-site budgeting for Private Advertising Technology.
System Prompt Architecture Research & Findings
Analyzes system prompt architectures from Claude Code, Cline, and Bolt.new to recommend modular, tool-centric improvements for Better-i18n's AI agent.
Questions and Answers to Supervised Learning.
Answers student questions about supervised learning, covering SVM, kernels, overfitting, cross-validation, and performance metrics.
readelfohj ets coding style.
Defines C coding style rules for the libdwarf and readelfobj projects, covering indentation, braces, naming, and memory safety.