HendrixinGenerative AIThe ten LLM metrics you need to monitor (and why)Learn how to get LLM observability and optimize LLM performanceAug 21Aug 21
HendrixinGenerative AI95% of LLM developers are missing these 3 key reliability setupsBoost your LLM App’s performance and user retention with these game-changing strategiesJul 31Jul 31
HendrixinGenerative AIWeek of Open-Source models: which is the best? Mistral Large 2 vs. Llama 3.1 405BThis week has been bustling with activity in the open-source AI community. Meta unveiled its new flagship model, Llama 3.1 405B, along with…Jul 28Jul 28
HendrixinAI AdvancesA YC startup’s first project — an LLM router (with code)We used this project to apply to Y Combinator and got accepted into YC W24Jul 25Jul 25
HendrixinAI AdvancesA new choice in small models: GPT-4o mini vs. GPT-3.5, Claude-3 Haiku, and Gemini 1.5 FlashTest results for GPT-4o mini and Claude-3 HaikuJul 19Jul 19
HendrixThe 2024 LLM Directory: Find the Best Models for Your Use CasesDiscover the Top 5 LLMs for Coding, Document Processing, Translation, and More in 2024Jul 10Jul 10
HendrixFine-Tuning LLMs with Custom DatasetsPreviously, we discussed methods to prevent LLM hallucinations, highlighting three main strategies: advanced prompting, retrieval-augmented…Jul 8Jul 8
Hendrix5 best LLM playgrounds in 2024Exploring the capabilities of LLMs has become more accessible and exciting in 2024, thanks to various innovative playgrounds. Whether…Jul 4Jul 4
HendrixHow to stop LLM hallucinations?Hallucinations in LLMs occur when they generate incorrect, nonsensical, or irrelevant content. These issues arise from the models’ reliance…Jun 28Jun 28
HendrixLLM Benchmarking: A complete guide to evaluating LLM in 2024New LLMs are released almost weekly. These models, whether open-sourced or flagship, each have unique strengths. Some excel in generating…Jun 26Jun 26