PinnedLars WiikApple WWDC 2024 Apple Intelligence and More!A summary of what’s new and what’s to come2d ago2d ago
PinnedLars WiikClaude Opus vs. GPT-4o vs. Gemini 1.5 ⭐ — Multilingual PerformancePerformance Analysis of Leading LLMsMay 24May 24
PinnedLars WiikGPT-4o vs. GPT-4 vs. Gemini 1.5 ⭐ — Performance AnalysisMeasuring English Language Understanding of OpenAI’s New Flagship ModelMay 1335May 1335
PinnedLars WiikOpenAI’s GPT-4o vs. Gemini 1.5 ⭐ Context Memory EvaluationNeedle in Haystack Evaluation— OpenAI vs. GoogleMay 195May 195
PinnedLars WiikBest Embedding Model 🌟 — OpenAI / Cohere / Google / E5 / BGEAn In-depth Comparison of Multilingual Embedding ModelsApr 74Apr 74
Lars WiikTop LLM Reasoning Evaluation ⭐OpenAI’s GPT-4 Omni vs. Google’s Gemini vs. Anthropic’s Claude Opus6d ago6d ago
Lars WiikLLM Instruction Placement in Prompts — It Matters a Lot! ⭐Gemini 1.5 — Evaluation of how instruction placement in large prompts affects qualityMay 31May 31
Lars WiikHow to use LLM APIs ⭐— OpenAI, Claude, GoogleExamples for GPT-4o, Claude 3 Opus, and Gemini 1.5May 251May 251
Lars WiikHow Modern Tokenization Works 🌟Multilingual Tokenization — Byte-pair Encoding, SentencePiece, and WordPiece. Unigram Language Model. LLM, Embedding, NLP, Machine…Apr 21Apr 21
Lars WiikHow to Build a Retrieval-Augmented Generation (RAG) System💡Learnings from a real-world RAG applicationMar 20Mar 20
