Let’s talk about LLMs

Everybody seems to agree we’re in the middle of _something_, though what, exactly, seems to be up for debate. It …

James Bennett

ARTIFICIAL INTELLIGENCE (40) – Natural Language Processing (18) Few-Shot Prompting

Few-shot prompting is a technique used with large language models where the model is given a small number of examples inside the prompt itself to show what kind of task it should perform and how the output should look. Importantly, the model is not retrained or fine-tuned. Instead, it learns on the fly from the examples provided in the context. This behavior is often called in-context learning. Emergent few-shot learning highlights that this ability of modelsl was not explicitly programmed, […]

https://yolandamuriel.com/2026/04/30/artificial-intelligence-40-natural-language-processing-18-few-shot-prompting/

ARTIFICIAL INTELLIGENCE (40) – Natural Language Processing (18) Few-Shot Prompting

Few-shot prompting is a technique used with large language models where the model is given a small number of examples inside the prompt itself to show what kind of task it should perform and how th…

ARTIFICIAL INTELLIGENCE (39) – Natural Language Processing (17) Historical Evolution of Language Models (NLP)

1948 – Bag-of-Words & Distributional Hypothesis Bag-of-Words (BoW): Text is represented as an unordered collection of words, ignoring grammar and word order. Only word frequency matters. Distributional Hypothesis: “A word is characterized by the company it keeps.” This idea states that words with similar meanings tend to appear in similar contexts. © Image. Rahul Sharma NLP: Bag of Words 1954 – N-gram Models N-gram Model: Predicts the next word in a sequence based on the […]

https://yolandamuriel.com/2026/04/28/artificial-intelligence-39-natural-language-processing-17-historical-evolution-of-language-models-nlp/

ARTIFICIAL INTELLIGENCE (39) – Natural Language Processing (17) Historical Evolution of Language Models (NLP)

1948 – Bag-of-Words & Distributional Hypothesis Bag-of-Words (BoW): Text is represented as an unordered collection of words, ignoring grammar and word order. Only word frequency matters. Distri…

ARTIFICIAL INTELLIGENCE (35) – Natural Language Processing (13) Understanding Attention in Sequence‑to‑Sequence Models

Sequence‑to‑sequence (Seq2Seq) models are a common type of neural network used in tasks where one sequence is transformed into another, such as machine translation, speech recognition, and image captioning. A typical Seq2Seq model is composed of two parts: an encoder and a decoder. Seq2Seq Models Without Attention In a traditional Seq2Seq model without attention, the encoder reads the entire input sequence (for example, a sentence in English or Chinese) and compresses all the […]

https://yolandamuriel.com/2026/04/19/artificial-intelligence-35-natural-language-processing-13-understanding-attention-in-sequence-to-sequence-models/

ARTIFICIAL INTELLIGENCE (35) – Natural Language Processing (13) Understanding Attention in Sequence‑to‑Sequence Models

Sequence‑to‑sequence (Seq2Seq) models are a common type of neural network used in tasks where one sequence is transformed into another, such as machine translation, speech recognition, and image ca…

FYI: Amazon's AI matches shelter pets with families using natural language queries: Amazon Ads and PetArmor combined natural language AI, generative video, and shelter construction to match adoptable dogs and cats with prospective families. https://ppc.land/amazons-ai-matches-shelter-pets-with-families-using-natural-language-queries/ #AdoptDontShop #PetAdoption #ShelterPets #AmazonAI #NaturalLanguageProcessing
Amazon's AI matches shelter pets with families using natural language queries

Amazon Ads and PetArmor combined natural language AI, generative video, and shelter construction to match adoptable dogs and cats with prospective families.

PPC Land
Emotion concepts and their function in a large language model

All modern language models sometimes act like they have emotions. What’s behind these behaviors? Our interpretability team investigates.

Open data

A topic-based overview of public repositories containing research data. Agricultural sciences: AQUASTAT Dissemination System, Global information system of the Food and Agriculture Organization of t...

Python for Data Science
Also, there are some #NLP storylines, mostly centered around using human #voice to control weapons #MacGyver #NaturalLanguageProcessing #AI

Teaching AI Ethics

Update: since I wrote this original post covering the nine areas, I've expanded each one into a complete article. Have a read through this post, and then when you're ready to dive deeper into AI ethics, check out the full series here. If you linked to this post as part of a course or university resource, I suggest updating your links with the complete series. https://leonfurze.com/ai-ethics/ As we head into the start of Term 1 it's already looking like Artificial Intelligence is going to be […]

https://leonfurze.com/2023/01/26/teaching-ai-ethics/

A Brief History of Artificial Intelligence

Like any complex technology, Artificial Intelligence has its roots in a number of fields. From philosophy to computer science, mathematics to linguistics, tracing the history of AI and automation is a difficult business. The field was officially named in the 1950s, but ideas about automated machines have existed since long before then. This is a history of the development of Artificial Intelligence from some of its earliest philosophical and theoretical inceptions through to modern day […]

https://leonfurze.com/2023/02/11/a-brief-history-of-artificial-intelligence/