Published inLevel Up CodingHow to Benchmark DeepSeek-R1 Distilled Models on GPQA Using Ollama and OpenAI’s simple-evalsSet up and run the GPQA-Diamond benchmark on DeepSeek-R1's distilled models locally to evaluate its reasoning capabilities.May 13A response icon1May 13A response icon1
Published inDataDrivenInvestorHow LLMs are Reshaping Financial Services: Real-World ExamplesExploring the practical use cases and specialized models that are driving innovation and efficiency across financial servicesMar 10A response icon1Mar 10A response icon1
Published inTDS ArchiveExposing Jailbreak Vulnerabilities in LLM Applications with ARTKITAutomated prompt-based testing to extract hidden passwords in the popular Gandalf challengeSep 25, 2024A response icon4Sep 25, 2024A response icon4
Published inLevel Up CodingInside the Leaked System Prompts of GPT-4, Gemini 1.5, Claude 3, and MoreUnveiling the shared strategies and key distinctions in the prompts behind the best LLMs from OpenAI, Google, and AnthropicApr 16, 2024A response icon8Apr 16, 2024A response icon8
Published inDataDrivenInvestorHow to Web Scrape Wikipedia with LLM AgentsSimple guide to using LangChain Agents and Tools with OpenAI’s LLMs and Function Calling for web scraping of WikipediaJan 3, 2024A response icon3Jan 3, 2024A response icon3
Published inTDS ArchiveGuide to ChatGPT’s Advanced Settings — Top P, Frequency Penalties, Temperature, and MoreUnlock the full potential of ChatGPT by optimizing extended configurations like Top P, frequency and presence penalties, stop sequences…Nov 7, 2023A response icon2Nov 7, 2023A response icon2
Published inBetter ProgrammingText-to-Audio Generation with Bark, Clearly ExplainedDiscover the capabilities and intricacies of Bark, the open-source Generative AI model for text-to-speech, text-to-sound, and text-to-musicOct 9, 2023A response icon6Oct 9, 2023A response icon6
Published inTDS ArchiveWhen AI Goes Astray: High-Profile Machine Learning Mishaps in the Real WorldA tour of infamous machine learning blunders and failures that caught the world’s attentionAug 19, 2023A response icon17Aug 19, 2023A response icon17
Published inTDS ArchiveRunning Llama 2 on CPU Inference Locally for Document Q&AClearly explained guide for running quantized open-source LLM applications on CPUs using LLama 2, C Transformers, GGML, and LangChainJul 18, 2023A response icon31Jul 18, 2023A response icon31
Published inTDS ArchivearXiv Keyword Extraction and Analysis Pipeline with KeyBERT and TaipyBuild a keyword analysis application in Python comprising a frontend user interface and backend pipelineApr 18, 2023A response icon2Apr 18, 2023A response icon2