RSSAmplifier

Blog

Bhavana AI

AI/ML insights and consulting

me.bhavanaai.comRSS feed ↗59 posts

Latest posts

The Datacenter and Beyond

VL2, FaRM, eRPC, Spanner, and CausalSim. The datacenter papers I don't remember, the ones I do, and what ten weeks of CS244C changed about how I think.

The Math Your Network Engineers Aren't Doing

Congestion control is half of computer systems. Four papers from Stanford's CS244C on fairness, adversarial networks, and why overprovisioning is the honest answer.

Consensus Is Tricky, and People Don't Want to Mess With It

Two-Phase Commit, Zookeeper, Raft, and Simplex. Four papers on consensus from Stanford's CS244C, and why mathematical perfection matters less than defense in depth.

The Internet Was an Argument

End-to-End Arguments, Tussle in Cyberspace, and Wallbleed. Three papers from Stanford's CS244C that reframed how I think about where intelligence belongs in a system.

I Ran 190 A/B Tests to See if MCP Tools Waste Tokens

190 controlled A/B tests show MCP costs 1.2-2x more tokens than CLI tools, but tool gaps -- not protocol overhead -- cause the real failures.

I Built My Own Tesla Data Pipeline for $9/Month (With AI Writing Most of the Code)

Every Tesla data service had a dealbreaker. So I built a streaming telemetry pipeline from scratch, with Claude doing the heavy lifting. Here's the decision process, the architecture, and what the data actually looks like.

Validating Embedding Models at Scale (Part B: Cross-Validation on 7,813 Entries)

56 hand-labeled entries said Azure OpenAI was the best embedding model. 7,813 entries with cross-validation say otherwise -- and reveal why F1 = 0.46 isn't a failure.

Comparing Embedding Models for a Knowledge Graph (Part A: The 56-Entry Test)

How I compared 4 embedding models for entity disambiguation in a Cosmere knowledge graph -- and what the metrics actually mean.

The Integral Problem: Why AI Isn't Moving the Productivity Needle

AI adoption and potential gain are inversely correlated -- the people who would benefit most aren't using the tools. Here's the research, the math, and what to do about it.

How I Set Up Claude Code to Run From My Phone (And What I Learned About tmux Along the Way)

A walkthrough of setting up remote access to Claude Code from an iPhone using Tailscale, mosh, and tmux, including the detours, dead ends, and the surprisingly simple setup I ended up with.

The Car Wash Test: Why the Model That Solved a Quantum Breakthrough Can't Wash Your Car

I tested 9 frontier AI models with a deceptively simple question. The results reveal a fascinating tension between statistical priors and reasoning ability.

Dev Log: February 15, 2026

Nanny Timesheet, Short Projects, Courses

Dev Log: February 14, 2026

Courses, OpenClaw, Short Projects, Personal Projects

Dev Log: February 13, 2026

courses, short-projects, openclaw

Where Should I Live?

An interactive map of 32,000 home sales in King and Snohomish County, with traffic-aware commute times to work and climbing gyms.

Dev Log: February 12, 2026

short-projects, courses, bhavanaai

Dev Log: February 11, 2026

courses, short-projects, bhavanaai

GitHub's Outage Problem Isn't About Azure

Analyzing 1,234 GitHub incidents from 2013-2026 to test whether rising outages correlate with the Azure migration or product expansion.

Every Breath You Take: Air Quality Across 277 Indian Cities

Analyzing daily PM2.5 and AQI data from 277 Indian cities to find that the most polluted places are small towns, not the metros that make headlines.

Dev Log: February 10, 2026

courses, openclaw, tools, bhavanaai blog, short projects

Dev Log: February 9, 2026

courses, personal-finance, Azure cleanup, openclaw

Dev Log: February 8, 2026

personal-finance, courses

Dev Log: February 7, 2026

personal-finance, courses, openclaw

Dev Log: February 6, 2026

courses, career, openclaw, personal-finance

Dev Log: February 5, 2026

courses, tools, openclaw, personal-finance

Dev Log: February 4, 2026

tools, openclaw, courses, personal-finance

Dev Log: February 3, 2026

courses, tools, openclaw, personal-finance

Dev Log: February 2, 2026

openclaw, tools, courses, personal-finance

Dev Log: February 1, 2026

courses, personal-finance, tools, openclaw

Dev Log: January 31, 2026

tools, openclaw, courses, personal-finance

Dev Log: January 30, 2026

courses, tools, openclaw

Dev Log: January 29, 2026

courses, tools, openclaw

Dev Log: January 28, 2026

courses, tools, openclaw

Dev Log: January 27, 2026

courses, career

Dev Log: January 26, 2026

courses

Dev Log: January 25, 2026

courses, claude-transcript-viewer, podcast-summarizer-v2

Dev Log: January 24, 2026

courses, podcast-summarizer-v2, claude-transcript-viewer

Dev Log: January 23, 2026

tools, podcast-summarizer-v2, claude-transcript-viewer, courses

Dev Log: January 22, 2026

tools, podcast-summarizer-v2

Dev Log: January 21, 2026

claude-code-transcripts, courses-stanford-cs244c, bhavanaai, tools

Dev Log: January 20, 2026

podcast-summarizer-v2, claude-code-transcripts, courses-stanford-cs244c-gavel

Dev Log: January 19, 2026

podcast-summarizer-v2, courses, tools

Dev Log: January 18, 2026

courses

Dev Log: January 17, 2026

podcast-summarizer-v2, courses, tools

Dev Log: January 16, 2026

courses, podcast-summarizer-v2, tools

Dev Log: January 15, 2026

podcast-summarizer-v2, career, courses

Dev Log: January 14, 2026

podcast-summarizer-v2, career, courses

Dev Log: January 13, 2026

courses

Dev Log: January 9, 2026

CS244 GPU scheduling traces, GFW censorship research

Dev Log: January 8, 2026

CS244 project research