PinnedInData Science CollectivebyTanmay Deshpande·Feb 14I Analyzed 163K Lines of Kuzu’s Codebase. Here’s Why Apple Wanted It.How a 10-person startup built the graph engine Apple’s on-device AI strategy was missing.A response icon6A response icon6
PinnedInData Science CollectivebyTanmay Deshpande·Feb 27Claude Code Has Opinions About Your Stack. You Should Pay Attention.New research shows shadcn/ui at 90%, Stripe at 91%, AWS at 0% — and a self-reinforcing loop most of the industry hasn’t noticed.A response icon17A response icon17
PinnedInData Science CollectivebyTanmay Deshpande·Jan 16The 6 Architectural Decisions That Separate Architects from BottlenecksDecide in under 5 minutes when to make irreversible decisions vs reversible betsA response icon6A response icon6
PinnedInData Science CollectivebyTanmay Deshpande·Feb 17, 20256 Must Know Agentic Workflow Design Patterns (and Their Key Trade-Offs)A guide to agentic workflows that balance performance, complexity, and reliability
PinnedInBetter ProgrammingbyTanmay Deshpande·Oct 12, 2020Modern-Day Architecture Design Patterns for Software ProfessionalsCircuit Breaker, CQRS, Event Sourcing, Sidecar, Backend-for-Frontend, and StranglerA response icon10A response icon10
Tanmay Deshpande·6d ago660 Claude Code Trials Show What Messy Code Really Costs an AI AgentThe agent got the same answers either way. The difference showed up on the bill
InData Science CollectivebyTanmay Deshpande·Jun 25I Fine-Tuned an AI Model on My Mac for Less Than a Cent, and You Can TooNo NVIDIA card, no cloud bill, no course. Just a small model, an afternoon, and one lesson worth more than the training.A response icon1A response icon1
Tanmay Deshpande·Jun 20Stop Choosing Between Qwen and Claude. The 70/30 Split That Pays for Both.The benchmark gap is real and almost irrelevant. What local models fail at, not what they score, tells you which tasks to keep in the…
InData Science CollectivebyTanmay Deshpande·Jun 13I Spent a Day on the “Python vs Rust” Fight in the AI Era. Rust Didn’t Win.Five programs, two languages, one laptop.
Tanmay Deshpande·Jun 9OpenAI Loses $17 Billion a Year. Your Index Fund Is Fine With It.A small committee just refused to bend a boring rule for the most valuable money-losers in history. Here’s why that quietly matters to your…
