PinnedPublished inAI AdvancesAdvanced Prompt Caching Techniques to Build Faster & Cheaper AI.Let’s implement semantic cache retrieval using Postgres with custom TTL & more.Mar 143Mar 143
PinnedPublished inAI AdvancesPrompt Engineering (for Everyday Tasks) Doesn’t Have to Be So ComplicatedHere’s your quick checklist to get high-quality responses every time.Mar 78Mar 78
PinnedPublished inTowards AITry This to Keep Your Python Code Clean ForeverA set-and-forget technique to automatically fix your code.Mar 123Mar 123
PinnedPublished inAI AdvancesSteal My Blueprint to Build and Deploy RAGs [In Minutes].Most RAGs are built on this stack; why would you redo it every time?Feb 45Feb 45
PinnedPublished inTDS ArchiveSkills a Data Scientist Must Have (But a Software Engineer Doesn’t)I guided a friend through her career transition to being an ML engineer.Jan 217Jan 217
Published inAI AdvancesA Timeline of Significant Discoveries That Led to Better AI Reasoning.How LLMs evolved to think — From few-shot chain-of-thoughts to chain of drafts.4d ago24d ago2
Published inAI AdvancesReranking Can Improve Your RAGs (But Not Without A Tweak)Rerank context with limited resources and create RAGs that perform effectively.Mar 10Mar 10
Published inAI AdvancesOne of These Will Be Your Favorite Chunking Technique For RAGs.Document splitting and RAGs beyond the basics.Feb 187Feb 187
Published inAI AdvancesExactly How Much vRAM (and Which GPU) Can Serve Your LLM?What if you still want to run a massive model in your small GPU?Feb 75Feb 75
Published inTowards AIResource-Efficient Fine-Tuning of DeepSeek-R1How to make DeepSeek R1 to reason with your private dataFeb 4Feb 4
