PinnedInTDS ArchivebyMichał Oleszak·Jan 29, 2023Self-Supervised Learning in Computer VisionHow to train models with only a few labeled examplesA response icon1A response icon1
PinnedInTDS ArchivebyMichał Oleszak·Mar 14, 2024Designing RAGsA guide to Retrieval-Augmented Generation design choices.A response icon10A response icon10
PinnedInTDS ArchivebyMichał Oleszak·Jan 14, 2024Evaluating Large Language ModelsHow do you know how good your LLM is? A complete guide.A response icon3A response icon3
InData Science CollectivebyMichał Oleszak·Mar 4Foundation Models ExplainedThe models powering the next generation of intelligent applications
InData Science CollectivebyMichał Oleszak·Feb 18Start Your Agent Evaluation RightA Quick Guide to Deepchecks Agent Evaluation
InData Science CollectivebyMichał Oleszak·Nov 17, 2025Detecting and Fixing Dead Neurons in Foundation ModelsHow to make neuron health actionableA response icon1A response icon1
InData Science CollectivebyMichał Oleszak·Nov 3, 2025Debugging and Improving RAG PipelinesUsing Root Cause Analysis to Detect and Fix Failures in LLM ApplicationsA response icon1A response icon1
InData Science CollectivebyMichał Oleszak·Aug 10, 2025Why Prompt Injection Still WorksAnd How to Catch It Before It’s Too Late
InTDS ArchivebyMichał Oleszak·Dec 11, 2024Transformers Key-Value (KV) Caching ExplainedSpeed up your LLM inferenceA response icon9A response icon9
InTDS ArchivebyMichał Oleszak·Sep 23, 2024Reinforcement Learning from Human Feedback (RLHF) for LLMsAn ultimate guide to the crucial technique behind Large Language ModelsA response icon1A response icon1
