32 items
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.
Build agentic workflows with LangChain and LangGraph using state graphs, tool routing, persistence, retries, and multi-step control.
Covers the 2021 Foundation Models Report published by Stanford's CRFM. Explains how this influential report formally defined foundation models.
Covers the mathematical foundations of LLM fine-tuning with clear explanations and minimal prerequisites.
Covers choosing the right approach for your LLM project: using pre-trained models as-is, enhancing them with context injection and RAG.
Covers the core concepts of LLM workflows: connecting language models to tools, handling responses, and building intelligent systems.
Covers Dense Passage Retrieval (DPR) and Retrieval-Augmented Generation (RAG), the 2020 innovations.
AI agents combine a language model with tools, memory, and control logic. This article separates agents from workflows and multi-agent systems.
The application of deep neural networks to speech recognition in 2012, led by Geoffrey Hinton and his colleagues, marked a major advance.
Model Context Protocol (MCP) gives LLM applications a standard way to list tools, call them, and exchange structured results across services.
Temperature zero does not make an LLM deterministic. GPU kernels, batching, floating-point arithmetic, and serving choices can still change its output.
DeepMind's WaveNet changed text-to-speech synthesis in 2016 by generating raw audio waveforms directly using neural networks.
In 2005, the PropBank project at the University of Pennsylvania added semantic role labels to the Penn Treebank.
In 1998, Charles Fillmore's FrameNet project at ICSI Berkeley released the first large-scale computational resource based on frame semantics.
In 2002, IBM researchers introduced BLEU (Bilingual Evaluation Understudy), revolutionizing machine translation evaluation.
Conditional Random Fields model structured predictions without assuming independent labels. Covers the 2001 paper, feature design, inference, and later uses.
Natural language processing underwent a fundamental shift from symbolic rules to statistical learning.
Claude Shannon's 1948 work on information theory introduced n-gram models, one of the most core concepts in natural language processing.
In 1950, Alan Turing proposed a deceptively simple test for machine intelligence, originally called the Imitation Game.
Joseph Weizenbaum's ELIZA, created in 1966, became the first computer program to hold something resembling a conversation.
Hidden Markov Models changed speech recognition in the 1970s by introducing a clever probabilistic approach.
In 1958, Frank Rosenblatt created the perceptron at Cornell Aeronautical Laboratory, the first artificial neural network.
In 1968, Terry Winograd's SHRDLU system demonstrated a major approach to natural language understanding by grounding language in a simulated blocks world.
Bernard Widrow and Marcian Hoff built MADALINE at Stanford in 1962, taking neural networks beyond the perceptron's limitations.
In 1991, IBM researchers changed machine translation by introducing the first broad statistical approach.
In 1995, RNNs changed sequence processing by introducing neural networks with memory: connections.
Hochreiter and Schmidhuber introduced LSTMs in 1997 to address vanishing gradients. Covers gated memory, long context, and later sequence models.
In the 1980s, neural networks hit a wall: nobody knew how to train deep models. That changed when Rumelhart, Hinton.
In the mid-1990s, Princeton University released WordNet, a major lexical database.
In 1988, Yann LeCun introduced Convolutional Neural Networks at Bell Labs, forever changing how machines process visual information.
In 1987, Slava Katz solved one of statistical language modeling's biggest problems. When your model encounters word sequences it has never seen before.
In 1987, Alex Waibel introduced Time Delay Neural Networks, a major architecture that changed how neural networks process sequential data.
In 2004, ROUGE and METEOR addressed critical limitations in BLEU's evaluation approach.
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.