Artificial Intelligence articles
Dirichlet Distribution Output Layers for Uncertainty in Classification
by Peter de Blanc + ChatGPT Deep Research about 2 months ago01
Motivation and Concept of Dirichlet Outputs In a standard classifier, the softmax output gives a single categorical distribution for each input, but it cannot express **uncertainty about that dist...Balancing Strength and Surprise in Adversarial AI
by Peter de Blanc + ChatGPT Deep Research about 2 months ago00
Mixed Strategies and Exploitability (Game-Theoretic Foundations) In classical game theory, randomized (mixed) strategies are often essential to avoid exploitation. A deterministic (pure) stra...Adarie Go Eval Project
by Peter de Blanc + ChatGPT Deep Research 2 months ago00
We're developing an eval (i.e. a benchmark) of Go-playing skill of language models. This is just a fun little research project and something we can use to test out deep research and the Adarie publis...Latent Features of Numbers Learned by Sequence Models
by Peter de Blanc + ChatGPT Deep Research 2 months ago00
Researchers have developed various ways to embed integers as distinct tokens in sequence modeling tasks (e.g. using OEIS data). In these approaches, each number is treated like a “word” with its own v...Semantic Dimensions in English Word Embeddings
by Peter de Blanc + ChatGPT Deep Research 2 months ago00
Introduction Word embeddings represent word meanings as points in a high-dimensional continuous space. An intriguing finding is that certain principal components or directions in these spaces c...Multilingual Latent Spaces and Language Interpolation
by Peter de Blanc + ChatGPT Deep Research 2 months ago00
Multilingual Neural Models and Language Embeddings: Modern neural NLP models often use multilingual architectures (e.g. multilingual Transformers like mBERT, mT5, mBART, or GPT-style models) tha...Python Libraries for Go (Baduk/Weiqi) in Research
by Peter de Blanc + ChatGPT Deep Research 2 months ago01
Introduction Researchers working with the game of Go often need tools to simulate games, parse game records, and leverage AI engines. Key requirements include: Board State Simulation: Giv...Tutorial: Building, Running, and Publishing a Custom LLM Evaluation
by Peter de Blanc + ChatGPT Deep Research 3 months ago00
Evaluating large language models (LLMs) on novel tasks (like game-playing) requires careful planning. This tutorial will guide you through designing a good evaluation ("eval"), preparing data, writing...LLMs Playing and Commentating on Go: Current State (2025)
by Peter de Blanc + ChatGPT Deep Research 3 months ago00
Published Evaluations Academic research has begun examining how general-purpose large language models (LLMs) handle strategy games like Go. One 2024 study introduced a hybrid approach combining L...