About 48 results
https://luminary.blog/techs/llm-loss-function · 8 Sep 2025
Exploring Cross-Entropy Loss in Large Language Models.
https://luminary.blog/techs/gptoss-and-gemma3 · 19 Aug 2025
GPT-OSS and Gemma 3: two new small-but-powerful language models pushing the boundaries.
https://luminary.blog/techs/positional-embeddings · 4 Aug 2025
The mathematical technique that teaches AI models where each word sits in a sequence.
https://luminary.blog/techs/09-token-to-embedding · 31 Jul 2025
How language models convert token IDs into meaningful vector representations that capture semantic relationships.
https://luminary.blog/techs/08-subword-tokenization-algorithms · 30 Jul 2025
Understanding the algorithms behind tokenization in Large Language Models.
https://luminary.blog/techs/07-llm-inference · 29 Jul 2025
Understanding how Large Language Models generate text through the inference process.
https://kylestratis.com/posts/also-announcing-ai-agents-with-model-context-protocol/index · 27 Jul 2025
Announcing the early release of my book on building AI agents with Anthropic's Model Context Protocol
https://anil.recoil.org/notes/kyutai-streaming-voice-mlx · 16 Jul 2025
Quick setup guide for running Kyutai's high-quality speech-to-text model locally on Mac using their MLX implementation.
https://jacob.blog/notes/next-token-prediction-llms · 3 Jun 2025
Large language models are fundamentally next-token (next-word) predictors: a sequence goes in, the model assigns probabilities over the vocabulary, and generation proceeds one token at a time—optionally sampling from the top few candidates for variety ra...
https://augment.ink/human-generated-content-9 · 1 Jun 2025
Hey there! It's good to be back on the blog. Over the past few months, I've been focused on setting up the foundations for A New Social. I couldn't have imagined this is where I'd end up after writing my Bridges & The Last Network Effect post, but here we...