LLM

TL;DR for operators The useful finding is not “LLMs can write lessons.” They can, in the same way a junior analyst can write a memo: quickly, plausibly, and with enough confidence to become dangerous if nobody reads it. The paper tests GPT-4o with retrieval-augmented generation (RAG) for creating interactive, scenario-based lessons used to train novice human tutors in online middle-school mathematics.1 The lesson topics are practical rather than ornamental: encouraging student independence, encouraging help-seeking behaviour, and persuading students to turn cameras on during online tutoring. ...

TL;DR for operators If your optimisation system can choose the route, assign the vehicle, or schedule the job but cannot explain why, the obvious temptation is to bolt on a chatbot and call the matter solved. That is also how one gets fluent nonsense with a user interface. The paper behind this article proposes a better pattern: let the LLM translate a user’s question into formal variables and logic, evaluate those variables against the actual Monte Carlo Tree Search tree, retrieve domain knowledge only when the question calls for it, and then generate the final natural-language explanation.1 The LLM is still useful, but it is no longer allowed to improvise the evidence. A small mercy, really. ...

A multilingual large language model developed by the BigScience initiative, capable of generating text in 46 languages and 13 programming languages.

A mid-sized member of Anthropic’s Claude 3 model family, optimized for balanced performance across reasoning, speed, and multimodal understanding.

An experimental LLM built using Keras 3 and JAX/TPU, designed to showcase research-focused model development on the Kaggle Models platform.

A 7-billion-parameter open-weight language model developed by Google, optimized for efficiency, safety, and general-purpose reasoning.

An open-weight language model released by xAI (Elon Musk’s AI company), intended for research and analysis, with performance comparable to top-tier 2023 models.

The next-generation model from xAI, built on a new architecture and fully integrated into X (formerly Twitter) as part of Elon Musk’s AI assistant efforts.

Meta’s 7B-parameter base language model from the LLaMA 2 series, designed for general-purpose pretraining and customizable fine-tuning.

Meta’s 7B-parameter instruction-tuned model optimized for chat, dialogue, and assistant-style applications.