PinnedInTDS ArchivebyClaudia Ng·Nov 28, 2024The Most Expensive Data Science Mistake I’ve Witnessed in My CareerWhy true success in machine learning goes beyond optimizing a single metricA response icon29A response icon29
PinnedInData Science CollectivebyClaudia Ng·Jun 516 Claude Code Commands That Actually Changed My WorkflowSixteen Claude Code slash commands for the model context window, planning, diffs, and spendA response icon1A response icon1
PinnedInData Science CollectivebyClaudia Ng·May 146 LLM Prompting Techniques for Data Scientists and Engineers in 2026Six techniques matched to six failure modes, including inconsistent output formats, shallow reasoning, instruction drift, and more.
PinnedInData Science CollectivebyClaudia Ng·Feb 20My $0 Monthly Local Agentic Coding WorkflowHow I bypassed Cursor’s limits and redirected Claude Code to a local inference engine for unlimited tokens.A response icon2A response icon2
InData Science CollectivebyClaudia Ng·Aug 13How to Build a Data Science Portfolio in the Age of Vibe-CodingWhat makes a portfolio project stand out when AI can write the code for you.A response icon1A response icon1
Claudia Ng·Jul 9I Built a $0 Hermes Agent I Text From TelegramHonest look at my always-on Hermes on a $0 cloud virtual machine + NVIDIA API free tier
InData Science CollectivebyClaudia Ng·Jul 2My $0 Hermes Agent SetupI wanted to try Hermes without paying for Portal, so I pointed the agent at NVIDIA’s free API tier instead.A response icon1A response icon1
Claudia Ng·Jul 2Prompt vs RAG vs Fine-Tuning: Which Fix Do You Need?Diagnose knowledge vs behavior failures, then choose prompting, retrieval, or training
InData Science CollectivebyClaudia Ng·Jun 15Glossary of Fine-Tuning Methods ExplainedSFT, LoRA, QLoRA, DPO, RLHF & GRPO: what each acronym means and how to pick the right fine-tuning method from the labels you already have.
Claudia Ng·Jun 8Fine-Tuning LLMs: When to Do It and When Not ToWhen LLM fine-tuning beats prompting and RAG and when to skip it
