RSSAmplifier

Blog

The Prompt & The Ponder

Technical writing on models, systems, and software by Serendeep Rudraraju.

blog.serendeep.techRSS feed ↗20 posts

Latest posts

Interpretability After the Transformer: We Changed the Architecture and Kept the Microscope

Mechanistic interpretability was built for softmax transformers. SSMs, diffusion LMs, and sparse MoE each dissolved one of its assumptions. Here's what that actually cost.

The Math Remembers: How to Catch a Model Lying About Being Original

A city shipped a 'homegrown' AI; subtraction proved most of it was someone else's. The toolkit for catching model fraud, and its honest limits.

Bounded Wrongness: A Field Guide to Probabilistic Data Structures

Bloom filters and their descendants trade a bounded, one-sided, tunable error for a space collapse exact structures can't match. The whole family, with the math.

The Rest of the Crate: Tempo, Key, and Never Stranding a File

Part 2 of building cratemind: the unglamorous 80%, tempo that lies by an octave, key from 1990s music theory, and a downloader that never quietly loses a track.

Your Music Has No Genre: Reading It Off the Waveform

Spotify deleted the BPM API and underground techno has no genre tag anywhere, so I stopped looking the genre up and started computing it from the audio.

Your Coding Agent Has Amnesia: It's the Harness, Not the Model

The same model behaves like a genius on small tasks and a goldfish on big ones. The bottleneck isn't intelligence. It's memory, and memory lives in the harness.

Memory as Polynomial Projection: The Mathematics of Long-Context Predictive Modeling

HiPPO's polynomial-projection idea is the through-line from S4 to Mamba-3 to HiSS. And it argues that long-context LLMs and long-context prediction are not the same problem.

Energy-Based Transformers: The 1982 Architecture Finally Got Compatible Training Tricks

An EBM finally crossed 800M parameters without collapsing. Nobody has independently reproduced the 35% scaling claim. Both halves matter.

The Open Source AI Lie: Weight-Washing, Broken Definitions, and Who Benefits

No major AI model meets the open source definition. Here's who's faking it, who benefits, and why the strongest argument against caring is uncomfortably real.

The Post-Transformer Era: State Space Models, Mamba, and What Comes After Attention

A practitioner's guide to Mamba and State Space Models — how selective state spaces achieve linear scaling, when to use SSMs vs Transformers vs hybrids, and production-ready models.

VLA Models Demystified: How Robots Learned to See, Listen, and Act

VLA models give robots the ability to see, parse language, and execute physical actions through a single architecture. This post covers how they work, what shipped in 2025, and where the limitations are.

JavaScript Date Is Broken. Here's What Replaces It

A tutorial on building a timezone-aware scheduler with React and the Temporal API, covering why Date fails at serious datetime work and how Temporal's type system prevents those bugs.

Open Source Sunday: Open Source Health Tools That Don't Sell You Out

Your fitness tracker is selling you out. The open source alternatives that aren't.

Context-Free Grammars Weren't Invented in the 1950s

The 2,500-year history of formal grammar, from Pāṇini's Sanskrit rules to BNF, and why someone proposed renaming it 'Panini-Backus Form' in 1967.

Towards Autonomous Edge AI: Local LLM Inference, Efficient Quantization, and Hybrid Memory in Practice

What if your AI worked offline, kept your secrets, and actually remembered you, without ever flinching at a spotty network? This post moves past the "API-everywhere" playbook. It lays out theory for a...

Building Truly Offline Apps Isn’t Magic: Local-First with Next.js, Flutter, and On-Device AI

Starting a new app, most of us wire up the backend before we even sketch the core screens -- then hope our offline mode just works later. It rarely does.

Flutter, But Organized: A Starter Template That Won’t Make You Cry in Debug

Starting a new Flutter project can get messy, fast. My first starter template turned into a cluttered mess, so I started over and built it right.

Cognitive Debt: Or, How I Forgot Why My Code Works

I've been vibe coding for a while now. Recently I stumbled across an article that put a name to the nagging feeling I've had for ages: Cognitive Debt.

JavaScript Dates Don’t Have to Be a Nightmare Anymore: Meet Temporal

Working with JavaScript's built-in Date object has always felt like defusing a bomb with oven mitts on. The Temporal API is here to fix this mess.

Installing Flutter on Arch: A Choose-Your-Own-Adventure Saga

Installing Flutter on Arch Linux is one of those tasks that sounds straightforward until you actually try it. Here are three paths ranked from grandma-friendly to why am I doing this to myself.