Skip to content

Large Language Models - Category Home

Large Language Models - Topics

What are Large Language Models (LLM)? How large is Claude's context window in practice? Prompting mistakes that waste Claude's long context How GPT models handle instructions Claude Opus for complex reasoning and multi-step problems Why ChatGPT answers the same prompt differently each time Handling long documents with the Claude API context window GPT vs o-series: when reasoning mode earns its cost What fits inside Claude's context window in practice Few-shot examples for consistent Claude output Claude Opus context limits in practice Why Claude Sonnet is the default choice for most work Why agent evals are harder than model evals Using ChatGPT without letting it make things up Why assistants struggle with long multi-step requests Post-training stages explained end to end Few-shot examples: how many is too many? Common mistakes when feeding ChatGPT a long document When fine-tuning beats prompting Chain-of-thought prompting with Claude: when it helps Why Claude's writing style sounds different from other chatbots Short-term vs long-term memory in an AI agent Tool descriptions matter more than the model Why does ChatGPT sometimes make things up? What is retrieval-augmented generation in a chatbot? Why do chatbots hallucinate wrong answers? How Claude Mythos differs from the main Claude models What an LLM context window really limits Why large AI models hallucinate at all How a large language model predicts the next token How RLHF shapes the tone of a language model Claude model tiers: which one to pick for coding vs writing