405 items · Page 6 of 9
Create a free account to keep your reading organized, join thoughtful discussions, and get more from every chapter.
Free to join · Takes less than a minute
Why
I created this space so readers can learn together, ask questions, and make sense of difficult ideas.
Covers continuous post-training, including parameter-efficient fine-tuning with LoRA, catastrophic forgetting prevention, incremental model updates.
Covers DBSCAN (Density-Based Spatial Clustering of Applications with Noise), the algorithm.
Covers GPT-4o, including unified multimodal architecture, real-time processing, unified tokenization, advanced attention mechanisms, memory mechanisms.
DeepSeek R1 uses reinforcement learning and distilled reasoning models for mathematical and coding tasks. Covers its training design, results, and limitations.
Covers agentic AI systems introduced in 2024. Explains how AI systems evolved from reactive tools to autonomous agents capable of planning.
AI co-scientist systems generate hypotheses, plan experiments, and synthesize evidence. Covers autonomous research workflows, evaluation, and human oversight.
Covers minimum cost flow optimization for slotting problems, including network flow theory, mathematical formulation.
Covers V-JEPA 2, including vision-based world modeling, joint embedding predictive architecture, visual prediction, embodied AI.
Covers word embeddings covering Word2Vec skip-gram, GloVe matrix factorization, negative sampling.
Covers Mixed Integer Linear Programming (MILP) for factory optimization, covering mathematical foundations, constraint modeling, branch-and-bound algorithms.
Covers specialized large language models for low-resource languages, including synthetic data generation, cross-lingual transfer learning.
Scale AI agents from single users to thousands while maintaining performance and controlling costs. Topics include horizontal scaling, load balancing.
Covers CP-SAT rostering using Google OR-Tools to solve complex workforce scheduling problems with binary decision variables, coverage constraints.
Covers Constitutional AI, including principle-based alignment, self-critique training, reinforcement learning from AI feedback (RLAIF), scalability advantages.
Reduce AI agent API costs without sacrificing capability. Topics include model selection, caching, batching, prompt optimization.
Covers practical techniques to make AI agents respond faster, including model selection strategies, response caching, streaming, parallel execution.
Maintain and update AI agents safely, manage costs, respond to user feedback, and keep your system healthy over months and years of operation.
Covers N-BEATS, an interpretable deep learning architecture for time series forecasting.
Monitor your deployed AI agent's health, handle errors gracefully, and build reliability through health checks, metrics tracking, error handling.
Covers GPT-4, including multimodal capabilities, improved reasoning abilities, enhanced safety and alignment, human-level performance on standardized tests.
Deploy your AI agent from a local script to a production service. Topics include packaging, cloud deployment, APIs, and making your agent accessible to users.
Covers HDBSCAN clustering algorithm covering density-based clustering, automatic cluster selection, noise detection.
Covers BIG-bench (Beyond the Imitation Game Benchmark) and MMLU (Massive Multitask Language Understanding), the widely used evaluation benchmarks.
Covers hierarchical clustering, including dendrograms, linkage criteria (single, complete, average, Ward), and scikit-learn implementation.
Covers function calling capabilities in language models from 2023, including structured outputs, tool interaction, API integration.
Control AI agent actions with least-privilege permissions, confirmation steps, and sandboxing. Covers tool allowlists, sensitive operations, and safe defaults.
QLoRA combines 4-bit quantization with low-rank adapters to fine-tune large language models on limited hardware while preserving model quality.
Implement content safety and moderation in AI agents, including system-level instructions, output filtering, pattern blocking, graceful refusals.
Covers SARIMA (Seasonal AutoRegressive Integrated Moving Average) for forecasting time series with seasonal patterns.
Whisper applies encoder-decoder transformers to multilingual speech recognition, translation, and language identification across noisy audio conditions.
Use observability for continuous agent improvement. Topics include patterns in logs, turn observations into targeted improvements, track quantitative metrics.
Covers exponential smoothing for time series forecasting, including simple, double (Holt's), and triple (Holt-Winters) methods.
Flamingo connects frozen vision and language models through gated cross-attention, supporting few-shot image and video tasks without task-specific fine-tuning.
Read agent logs, trace reasoning chains, identify common problems, and systematically debug AI agents.
Add logging to AI agents to debug behavior, track decisions, and monitor tool usage. Includes practical Python examples.
Explains how the unigram LM tokenizer trains via the EM algorithm, uses Viterbi decoding for segmentation, and enables subword regularization.
Covers Prophet time series forecasting including additive decomposition, trend modeling, seasonal patterns, and holiday effects.
Covers HELM (Holistic Evaluation of Language Models), the early evaluation framework.
Create feedback loops that continuously improve your AI agent through real-world usage data, pattern analysis, and targeted improvements.
Build agentic workflows with LangChain and LangGraph using state graphs, tool routing, persistence, retries, and multi-step control.
Explains why traditional word-level approaches fail with diverse text, from OOV words to morphological complexity.
Covers multi-vector retrieval systems introduced in 2021. Explains how token-level contextualized embeddings enabled fine-grained matching.
Create and use test cases to evaluate AI agent performance. Build broad test suites, track results over time.
Explains how WordPiece differs from BPE by using a likelihood objective for merges. Topics include the PMI score, greedy tokenization, ## prefix notation.
Chain-of-thought prompting elicits intermediate reasoning steps from language models. Covers zero-shot and few-shot methods, benefits, and limits.
Define clear, measurable success criteria for AI agents including correctness, reliability, efficiency, safety.
Examines the trade-offs of multi-agent AI systems, from specialization and parallel processing to coordination challenges and complexity management.
Covers the mathematical foundations of LLM fine-tuning with clear explanations and minimal prerequisites.
Create a free account to keep your reading organized, join thoughtful discussions, and get more from every chapter.
Free to join · Takes less than a minute
Why
I created this space so readers can learn together, ask questions, and make sense of difficult ideas.