Thinking in Public

A personal archive for independent long-term builders — engineering, A.I., drones, systems, and the life around the work.

Engineering & Life

Latest Articles

What Is A CPU PMU? How perf, VTune And Advisor Measure What A Processor Actually Did

What Is A CPU PMU? How perf, VTune And Advisor Measure What A Processor Actually Did

AMD EPYC AMD uProf AMX AVX-512 C-Kernel-Engine CPU Intel Advisor Linux perf performance engineering PMU VTune Xeon 35 min read
CPU measurement hardware A profiler does not infer retired instructions, cache misses, branch mispredictions, or memory-controller traffic from elapsed time. Event logic distributed through the processor emits signals. Performance-monitoring hardware selects some of those signals, increments counters, and optionally interrupts the CPU so Linux can record where the event occurred. PMU mea...
AS
Anthony Shivakumar
6 hours ago

Subscribe

Get my rants delivered to your inbox

I will send new posts as and when I write. No fixed cadence, just engineering notes, rants, and things I am thinking through.

Micro-Log

Quick Updates

Posts tagged #update ×
ANSH
24th Dec 2025
Wrote a blog after a while. Been busy, but I'm finding a good rhythm working on two things simultaneously: my C-Kernel-Engine and improving ANTSAND...
#update
Read more →

Annual Archives

Year End Reviews

2025: Fighting Banks, Writing C, and The Great Untangling

Year end review 6 min read
Looking back, 2025 has been a good year. Actually, it has been a transformative one.It was a year defined by taking control, whether that was taking control of my code by removing bloated frameworks, taking control of my rights against a billion-dollar bank, or simply having the time during the strike to rethink where I want to go.Here is the breakdown of a very busy year.The Legal Battle: David v...
AS
Anthony Shivakumar
31st Dec 2025

Reflecting on 2024

Year end review 4 min read
Alright, so 2024 is officially in the books. It had a few bumps along the way, but overall, it's been a pretty solid year. I managed to carry over some good habits from 2023, which definitely kept my momentum going. Heres my rundown:Mortgage PaymentsI stayed aggressive with my mortgage payments this year, aiming to chip away at my debt as much as possible. Im happy with my progress and might slow ...
AS
Anthony Shivakumar
31st Dec 2024

Reflecting on 2023: A Year in Review

Year end review 3 min read
This has been a year that felt both lengthy and fleeting, and there are a few standout moments I'd like to share. Financial Milestone: Mortgage Payoff Journey One significant goal has been my determined effort to liberate myself from the clutches of a mortgage within the next 2-3 years. This ambitious venture entails meticulous planning, calculating the optimal amount to allocate to my mortg...
AS
Anthony Shivakumar
1st Jan 2024

Year end review 2022

Year end review 1 min read
I seem to be writing blogs once a year. Not ideal but good enough. So, what has happened in 2022 and what do I plan to do in 2023?1. Had a baby girl2. Invest a lot more into my lab3. Spent more time learning electronic hardware design principles4.Able to invest time and grow my you tube channel5. Got a 3d printer
AS
Anthony Shivakumar
2nd Jan 2023

Year end review 2021

Year end review 4 min read
It has been almost a year since I have written on this blog. This year has been interesting. So what has happened?1. I got marriedThis year in July I had got married. Life does not feel different as we have been together for the last 4-5 years. Now that it is official, it makes things feel different. I need to tell people I am now married and not single. Overall this has been the highlight of my y...
AS
Anthony Shivakumar
1st Jan 2022

My year end review 2020

Year end review 9 min read
The year 2020 has finally come to an end. What a year. In this blog, I want to share what I did, what I learned, what I have transformed into, and what I plan to do in 2021.The year started well, with a bunch of well-paying clients. ANTSAND agency was taking off. By March when covid-19 started to take a hit, things started to slow down. It was during this time I focused all my attention on develop...
AS
Anthony Shivakumar
31st Dec 2020

Need an intelligent system to work on real hardware?

Embedded systems · Robotics · Constrained AI · CPU and HPC · Accelerators · Distributed systems

Work With Us / Antshiv Robotics

Engineering & Life

Articles

What kernel.kptr_restrict=0 Actually Does: Linux Profiling, Kernel Symbols, VTune And Advisor

What kernel.kptr_restrict=0 Actually Does: Linux Profiling, Kernel Symbols, VTune And Advisor

C-Kernel-Engine Intel Advisor kernel engineering Linux performance profiling VTune 13 min read
Linux profiling permissions kernel.kptr_restrict=0 does not unlock CPU counters. It changes whether kernel addresses can be exposed and resolved. That matters for kernel attribution, but it is a different permission from collecting performance events. User-space symbols, kernel-pointer visibility, and PMU counter access are separate evidence boundaries. Profiling becomes reliable when...
AS
Anthony Shivakumar
1 day ago

Nemotron Kernels From Inference To Backpropagation

backpropagation C-Kernel-Engine control systems Conv1D CPU AI Kalman filter kernel mathematics Mamba2 memory hierarchy Mixture of Experts Nemotron NVIDIA NeMo quantization Qwen signal processing state space 29 min read
Nemotron kernel lifecycle Supporting a model for inference is not the same as supporting its training graph. Every kernel needs a forward equation, saved-state contract, reverse equation, precision policy, and independent reference. Nemotron kernel series: the third step Begin with Nemotron Architecture From A C-Kernel-Engine Runtime Perspective for the complete runtime map: hybri...
AS
Anthony Shivakumar
2 days ago
Nemotron Is Not One Circuit: Mamba, Attention, And MoE Routing

Nemotron Is Not One Circuit: Mamba, Attention, And MoE Routing

C-Kernel-Engine CPU AI kernel engineering Mamba2 Mixture of Experts Nemotron numerical parity NVIDIA NeMo 12 min read
Nemotron architecture note A hybrid model is not one block repeated many times. Mamba state, attention history, router decisions, and expert weights create different execution and memory contracts. Nemotron kernel series: architecture to execution Start with Nemotron Architecture From A C-Kernel-Engine Runtime Perspective. That report maps the complete hybrid runtime surface: atte...
AS
Anthony Shivakumar
3 days ago

Gemma4-VL In CKE: How Images Become Decoder Tokens

C-Kernel-Engine CPU AI Gemma4-VL multimodal AI RoPE vision transformer 15 min read
Gemma4-VL compatibility A multimodal model is not magic. The image becomes patches, patches become embeddings, and embeddings become a prefix the decoder can consume. A vision-language model is not magic. The decoder does not consume pixels. The image is resized, divided into patches, embedded by a vision encoder, projected into the decoder dimension, and inserted into the token str...
AS
Anthony Shivakumar
4 days ago

Gemma4 In CKE: Four Attention Paths, Shared KV, And Sliding Windows

C-Kernel-Engine CPU AI Gemma4 kernel maps RoPE shared KV sliding attention 9 min read
Gemma4 architecture Gemma4 in C-Kernel-Engine is not one attention kernel. It is a per-layer contract that dispatches among four paths: full or sliding attention, each with either owned or shared KV. It is easy to summarize Gemma4 as a model with sliding-window attention. That description is incomplete. The current C-Kernel-Engine v8 circuit has to represent several interacting dec
AS
Anthony Shivakumar
5 days ago

Templates Are Circuit Maps: How CKE Describes A Model Family

c-kernel-engine cpu-inference generated-c graphir kernel-engineering loweredir model-runtime templates 43 min read
Templates Are Circuit Maps: How CKE Describes A Model Family C-Kernel-Engine hardening note A CKE template is not decoration. It is the circuit map that tells the compiler what model path exists before any C code is emitted. In C-Kernel-Engine, model support should not begin with a pile of special cases hidden inside generated C. It should begin with an explicit circuit m...
AS
Anthony Shivakumar
6 days ago

GGUF: The File Format That Made Local LLMs Practical

c-kernel-engine cpu-inference gguf local-llm quantization 28 min read
GGUF: The File Format That Made Local LLMs Practical Format deep dive GGUF is not just a container for weights. It is a single-file deployment unit that carries the model architecture, tokenizer, quantization metadata, and tensor data everything needed to go from file open to first token with zero external dependencies. If you have ever downloaded a model from Hugging
AS
Anthony Shivakumar
1 week ago

Amdahl's Law, Theory Of Constraints, And C-Kernel-Engine Optimization

amdahls-law c-kernel-engine cpu-inference distributed-cpu-ai linux performance-engineering theory-of-constraints 14 min read
CPU runtime optimization note Amdahl's Law explains the mathematical ceiling. Theory of Constraints explains the engineering discipline. C-Kernel-Engine needs both: measure the slowest part of the runtime, improve that constraint, then remeasure the whole pipeline. Amdahl's Law is the fastest way to stop pretending that more cores automatically mean...
AS
Anthony Shivakumar
1 week ago

DeepSeek-V4 Architecture From Kernels: mHC, CSA, HCA, DSA, and C-Kernel-Engine

ai runtime attention c-kernel-engine cpu ai deepseek kernels moe transformers 26 min read
Architecture note This is a DeepSeek architecture report for the C-Kernel-Engine path. The goal is not to summarize the paper casually. The goal is to convert the architecture into kernels, memory layouts, test contracts, and build order. It sits next to the earlier ShivasNotes notes on Nemotron architecture, DeltaNet versus SSM, KV cache memory, and K-quants. .blog-math-display { ma...
AS
Anthony Shivakumar
1 week ago

MOSFET DUT Characterization Pipeline: Rebuilding My Drone ESC Work From Measurements

antshiv robotics drones esc kicad mosfet ngspice power electronics robotics 14 min read
Lab note I am restarting my BLDC ESC work by turning old MOSFET videos, NXP reference designs, datasheets, SPICE models, KiCad, ngspice, and actual lab measurements into one repeatable characterization pipeline. I have been circling this problem for years. If you look through my ANTSHIV ROBOTICS YouTube channel, there are older videos where I talk through MOSFET internals, MOSFET...
AS
Anthony Shivakumar
1 week ago

How the Jacobian Matrix Works

ai-kernels backprop c-kernel-engine deep-learning jacobian linear-algebra machine-learning systems-programming 22 min read
.jacobian-matrix-post .math-block { display: block; max-width: 100%; overflow-x: auto; overflow-y: hidden; -webkit-overflow-scrolling: touch; margin: 1rem 0; padding: 0.85rem 1rem; border: 1px solid #e5e7eb; border-radius: 10px; background: #f8fafc; color: #111827; line-height: 1.7; white-space: nowrap; } .jacobian-matrix-post .math-block...
AS
Anthony Shivakumar
1 week ago

How Audio Transformers Work: The Encoder Path, Whisper, Timestamps, And Why Audio Is Not A VLM Patch

audio-transformer c-kernel-engine encoder-decoder speech-recognition transformers whisper 16 min read
How Audio Transformers Work: The Encoder Path, Whisper, Timestamps, And Why Audio Is Not A VLM Patch Audio transformers use the same high-level trick as language and vision transformers: convert the input into a sequence of dense vectors, then let attention mix information across that sequence. But the front end is different. Text starts with tokens. Vision starts with image patches. Audio s...
AS
Anthony Shivakumar
1 week ago

DeltaNet vs SSM: Two Fixed-Size Memory Systems Beyond Attention

ai-kernels attention c-kernel-engine cpu-inference deltanet hybrid-models mamba ssm systems-programming 18 min read
C-Kernel-Engine architecture note DeltaNet and SSM/Mamba are two ways to reduce the amount of unbounded attention history a model has to carry by introducing fixed-size learned state. They are often described with the same vague phrase: linear attention or recurrent attention. That is not enough for C-Kernel-Engine. CKE has to know what state is carried, what kern
AS
Anthony Shivakumar
1 week ago
Nemotron Architecture From A C-Kernel-Engine Runtime Perspective

Nemotron Architecture From A C-Kernel-Engine Runtime Perspective

ai-kernels c-kernel-engine cpu-inference mamba2 moe nemotron state-space-models systems-programming 16 min read
C-Kernel-Engine architecture note Nemotron-style hybrid models are interesting to C-Kernel-Engine because they stop looking like a simple stack of attention plus MLP blocks. A runtime has to handle attention, Mamba2 state-space recurrence, routed MoE experts, ReLU2 expert math, tokenizer guardrails, memory planning, and architecture-specific lowering without turning the implementatio...
AS
Anthony Shivakumar
1 week ago
K-Quants Deep Dive: Q4_K, Q5_K, Q6_K, Q8_K And Mixed Dot Products

K-Quants Deep Dive: Q4_K, Q5_K, Q6_K, Q8_K And Mixed Dot Products

ai-kernels c-kernel-engine cpu-inference k-quants q4-k q6-k quantization systems-programming 18 min read
ML systems Quantization internals This ShivasNotes deep dive is the granular companion to the broader Quantization Deep Dive in this series. The earlier post explained why quantization matters for CPU inference. This one opens the K-quant formats themselves: Q4_K, Q5_K, Q6_K, Q8_K, and the mixed K Q8_K dot products that C-Kernel-Engine has to execute correctly. The thesis is simple
AS
Anthony Shivakumar
2 weeks ago

Threadpools And Memory Pools: Why CKE Needs Runtime Ownership For CPU AI Kernels

ai-kernels c-kernel-engine cpu-inference linux-performance memory-pool pthreads systems-programming threadpool 11 min read
C-Kernel-Engine runtime comparison This post is a follow-up to the earlier thread-pool deep dive. The previous post built the pthread idea from first principles. This one asks the systems question: when should a CPU-native AI runtime own its threadpool and memory pools instead of letting every kernel, library, allocator, or framework layer make hidden decisions? In the earlier post...
AS
Anthony Shivakumar
2 weeks ago
Pipeline vs Tensor Parallelism: How CKE Splits AI Across CPU Nodes

Pipeline vs Tensor Parallelism: How CKE Splits AI Across CPU Nodes

c-kernel-engine cpu inference distributed cpu ai mpi pipeline parallelism rdma tensor parallelism 15 min read
Distributed runtime note C-Kernel-Engine has been hardened first as a CPU-native runtime on single machines. The next phase is not just buying faster CPUs. It is learning how to make multiple CPU nodes cooperate without turning the runtime into a black box. The previous distributed CPU post framed the larger systems bet: cheap replaceable CPU nodes, Linux control, explicit memory layout,...
AS
Anthony Shivakumar
2 weeks ago

Distributed CPU AI: MPI, RDMA, NUMA, and C-Kernel-Engine

c-kernel-engine distributed-cpu-ai mpi numa rdma systems-programming 13 min read
Systems note This post moves from model math into the machine that actually runs the kernels: cores, caches, NUMA domains, MPI ranks, RDMA-capable fabrics, and the memory-layout discipline needed for distributed CPU AI. .blog-math-display { margin: 1.4rem 0; padding: 1.25rem 1.5rem; border: 1px solid rgba(52, 211, 153, 0.28); border-radius: 20px; background: rad...
AS
Anthony Shivakumar
2 weeks ago
Muon Optimizer: SGD vs AdamW vs Matrix-Aware Training Updates

Muon Optimizer: SGD vs AdamW vs Matrix-Aware Training Updates

adamw c-kernel-engine muon optimizer pytorch training-kernels 17 min read
Optimizer research note This post continues the path established in Optimizers: From SGD to AdamW. Muon is a matrix-aware training update that changes what the optimizer kernel has to compute, store, and validate. .blog-math-display { margin: 1.4rem 0; padding: 1.25rem 1.5rem; border: 1px solid rgba(56, 189, 248, 0.28); border-radius: 20px; background: radial-gr...
AS
Anthony Shivakumar
2 weeks ago
Kernel Engineers Are Worth Billions In 2026: Chris Lattner, Mojo, LLVM, and the Compiler Layer of AI

Kernel Engineers Are Worth Billions In 2026: Chris Lattner, Mojo, LLVM, and the Compiler Layer of AI

ai-infrastructure c-kernel-engine compiler-engineering kernel-engineering mojo 16 min read
Kernel Engineers Are Worth Billions In 2026: Chris Lattner, Mojo, LLVM, and the Compiler Layer of AI Compiler systems note Chris Lattner's career is a reminder that compiler engineers and kernel engineers are not becoming less valuable in the AI era. They may be becoming more valuable, because every serious AI system eventually has to become executable math on real hardware. ...
AS
Anthony Shivakumar
2 weeks ago
Linux System Programming For AI Kernels: Core Pinning, Huge Pages, TLBs, NUMA, and Memory Discipline

Linux System Programming For AI Kernels: Core Pinning, Huge Pages, TLBs, NUMA, and Memory Discipline

ai kernels c-kernel-engine linux performance engineering systems programming 31 min read
Systems note A fast kernel is not just a loop. A fast kernel is a loop, a memory layout, a thread placement policy, a page-fault policy, and a measurement discipline running inside a real Linux system. When people first learn AI performance engineering, they usually start with the visible math: matrix multiplication, attention, normalization, quantization, SIMD, a...
AS
Anthony Shivakumar
2 weeks ago
KV Cache Memory: The Hidden State That Makes LLM Decode Work

KV Cache Memory: The Hidden State That Makes LLM Decode Work

attention c-kernel-engine kv-cache llm-inference memory systems 43 min read
KV cache memory for CPU-native inference This ShivasNotes deep dive is written for engineers who want to understand the single largest memory consumer in autoregressive LLM inference: the KV cache. Without it, every decode token recomputes all keys and values from scratch O(T) work. With it, inference becomes O(T) per token, but you trade compute for memory. C-Kernel-Engine handles KV c
AS
Anthony Shivakumar
3 weeks ago
v8 IR Pipeline Codegen: How CKE Hardens Pure-C Inference

v8 IR Pipeline Codegen: How CKE Hardens Pure-C Inference

c-kernel-engine codegen compiler inference ir systems 38 min read
v8 inference hardening This ShivasNotes deep dive is written for engineers who want to understand what happens between "here is a model on Hugging Face" and "here is a compiled .so that runs inference in pure C." C-Kernel-Engine is not a runtime interpreter it is a code generator. Template JSON defines the architecture. The IR builder resolves kernels. The memory planner assigns every byt
AS
Anthony Shivakumar
3 weeks ago
AI Kernels You Should Know To Learn Deep Neural Networks

AI Kernels You Should Know To Learn Deep Neural Networks

ai kernels cpu inference deep learning kernel engineering shivasnotes 20 min read
AI kernel learning map This post is a bridge between the earlier ShivasNotes fundamentals series and the next long-form video: what AI kernels should you actually know if you want to understand deep neural networks from math to runtime? A neural network is not one giant mysterious operation. It is a graph of smaller kernels: matrix multiplies, activation functions, normalization, attenti...
AS
Anthony Shivakumar
3 weeks ago
CPU Performance Engineering for AI: Rooflines, Flamegraphs, VTune, and Perf Gates

CPU Performance Engineering for AI: Rooflines, Flamegraphs, VTune, and Perf Gates

ai-kernels c-kernel-engine cpu-performance flamegraph perf roofline vtune 41 min read
CPU performance engineering C-Kernel-Engine This ShivasNotes deep dive is written for CPU silicon teams and systems engineers who need to understand not just whether an AI framework is fast, but why it is or isn't fast, and exactly where the bottleneck lives. C-Kernel-Engine doesn't just run inference it generates a full performance observatory with roofline analysis, flamegraphs, VTun
AS
Anthony Shivakumar
3 weeks ago
Flash Attention on CPU: Online Softmax, Cache Discipline, and C-Kernel-Engine

Flash Attention on CPU: Online Softmax, Cache Discipline, and C-Kernel-Engine

attention avx512 c-kernel-engine cpu-kernels flash-attention online-softmax simd 50 min read
ML fundamentals This ShivasNotes deep dive is written for CPU silicon teams asking a very specific question: does C-Kernel-Engine really own attention on CPU down at the kernel layer? The answer is yes. The implementation spans flash attention, the public docs, and a full attention surface of 9,187 lines across 10 files, with the video walkthrough companion on youtube.com/@antshivrobotics. ...
AS
Anthony Shivakumar
3 weeks ago
Quantization Deep Dive: How CPU Kernels Compress Weights and Preserve Accuracy

Quantization Deep Dive: How CPU Kernels Compress Weights and Preserve Accuracy

ai kernels amx c-kernel-engine cpu inference quantization simd vnni 39 min read
Quantization deep dive ML fundamentals This ShivasNotes deep dive is written for CPU silicon teams evaluating whether C-Kernel-Engine really owns its quantized inference path. The answer is yes: quantization in C-Kernel-Engine is handwritten kernel code, documented at the quantization deep dive and the format reference, with the walkthrough companion on youtube.com/@antshivrobotics@shivasn
AS
Anthony Shivakumar
3 weeks ago
ARM NEON in C-Kernel-Engine: Real Quantized Kernels on ARM

ARM NEON in C-Kernel-Engine: Real Quantized Kernels on ARM

ai-kernels arm-neon c-kernel-engine cpu-inference simd 37 min read
ARM NEON C-Kernel-Engine CKE has already run Qwen2 and Qwen3 on ARM Cortex-A72 hardware (TI TDA4VM). This is not a roadmap post. This is a what we already ship post. For ARM silicon teams, the important fact is simple: C-Kernel-Engine already contains production NEON kernel paths for quantized inference, and the companion architectural walkthrough is on youtube.com/@antshivrobotics.
AS
Anthony Shivakumar
3 weeks ago
SIMD Deep Dive: How AI Kernels Use SSE, AVX, AVX-512, and VNNI

SIMD Deep Dive: How AI Kernels Use SSE, AVX, AVX-512, and VNNI

adamw avx avx512 c-kernel-engine cpu-inference deltanet quantization rmsnorm simd vnni 42 min read
ML fundamentals SIMD deep dive This ShivasNotes deep dive is written for CPU silicon teams evaluating kernel-level software competence. The subject is not can the model run? but how explicitly does the software map ML math onto the ISA? Every code block below comes from the real C-Kernel-Engine production tree, and the companion walkthrough lives at youtube.com/@antshivrobotics
AS
Anthony Shivakumar
4 weeks ago
How Qwen3-VL Vision Works: Header Body Footer

How Qwen3-VL Vision Works: Header Body Footer

attention c-kernel-engine multimodal qwen3-vl vision-transformer 27 min read
Lab note This ShivasNotes lab note studies how a real vision-language model turns images into tokens that a language decoder can use. It connects earlier notes on activations, normalization, attention, residual connections, full backprop, optimizers, and DeltaNet. This is where those abstractions stop being classroom diagrams and become one real production vision-language stack. ...
AS
Anthony Shivakumar
4 weeks ago
Gated DeltaNet: Recurrent Attention With Error-Driven Memory

Gated DeltaNet: Recurrent Attention With Error-Driven Memory

attention backprop c-kernel-engine deltanet qwen 27 min read
Lab note This ShivasNotes lab note studies the alternative used by the Qwen3.5 / qwen3next recurrent path in C-Kernel-Engine: Gated DeltaNet, where the model stops trying to store every token verbatim and instead learns to store only the correction its memory still needs. It builds on the earlier attention derivation in Attention: The Core Of The Transformer. Speaker note. The key nar...
AS
Anthony Shivakumar
16th Jun 2026
Optimizers: From SGD to AdamW

Optimizers: From SGD to AdamW

adamw ai kernel engineering c kernel engine llm training optimizers sgd 9 min read
Lab note Part of the ShivasNotes transformer-from-scratch series. Previously: dL/d(LLM): The Full Backward Pass. The full backward-pass post ended with every weight in the model holding a gradient. This post is about the step that actually changes those weights. The optimizer takes the raw gradient signal and turns it into a weight update. How that update is computed determine...
AS
Anthony Shivakumar
15th Jun 2026
AI Kernel Engineer Beginner Guide: Math, Linear Algebra, C/Linux

AI Kernel Engineer Beginner Guide: Math, Linear Algebra, C/Linux

ai kernel engineering c kernel engine c programming calculus linear algebra linux shivasnotes systems programming 8 min read
AI Kernel Engineer Beginner Guide: Math, Linear Algebra, C/Linux Part 1: Beginner roadmap A viewer asked a useful question: I know some C, some linear algebra, and some calculus. What are the prerequisites to learn this? My answer is not learn all of mathematics first. This beginner guide is the first layer: learn enough calculus to read gradients, enough linear
AS
Anthony Shivakumar
14th Jun 2026
Thread Pools in C: How CPU Runtimes Dispatch Work Across Cores

Thread Pools in C: How CPU Runtimes Dispatch Work Across Cores

c c-kernel-engine cpu runtime kernel engineering threadpools 23 min read
Thread Pools in C: How CPU Runtimes Dispatch Work Across Cores Runtime note Companion note for the threadpool video. This post zooms into the local runtime layer: how persistent workers receive work, how fn(ith, nth, arg) turns one C function into core-parallel execution, and why CPU AI runtimes should not create threads inside hot kernels. Companion material This post is paired ...
AS
Anthony Shivakumar
13th Jun 2026
dL/d(LLM): The Full Backward Pass

dL/d(LLM): The Full Backward Pass

backpropagation c-kernel-engine llm training transformers 31 min read
Lab note Previously: Residual Connections: The Gradient Highway. This is the capstone post of the transformer-building-block series. The previous entries in this series built every kernel a transformer needs. Scalar operations, matrix multiplies, softmax, layer normalization, positional encoding, tokenization, attention, and residual connections. Each post showed the forward pass...
AS
Anthony Shivakumar
12th Jun 2026
Residual Connections: The Gradient Highway

Residual Connections: The Gradient Highway

backpropagation C-Kernel-Engine machine learning Pre-LN residual connections ResNet transformers 24 min read
Lab note Previously: Attention: The Core Of The Transformer. The previous post showed how attention routes information sideways across a sequence. This post is about the architectural trick that lets that routing stack to enormous depth without collapsing during training. Residual connections are the gradient highway underneath the entire transformer era. If one idea dese...
AS
Anthony Shivakumar
11th Jun 2026
Attention: The Core Of The Transformer

Attention: The Core Of The Transformer

attention backpropagation C-Kernel-Engine Flash Attention GQA machine learning QKV transformers 33 min read
Lab note Previously: Tokenization: The First Decision That Shapes Everything. The previous post ended with tokens becoming vectors. This post is where those vectors finally start talking to one another. Full attention is the moment a transformer turns a row of isolated embeddings into a context-aware state where every token can measure every other token, route information selectiv...
AS
Anthony Shivakumar
10th Jun 2026
Tokenization: The First Decision That Shapes Everything

Tokenization: The First Decision That Shapes Everything

BPE C-Kernel-Engine machine learning SentencePiece tokenization transformers WordPiece 27 min read
Lab note Companion post to the Tokenization carousel. Previously: Positional Encoding: Teaching Transformers Where To Look. Tokenization is the first place where text stops being human language and starts becoming machine state. A model never reads a paragraph the way you or I do. It reads a sequence of integer IDs emitted by a tokenizer, and every downstream tensor operation trea...
AS
Anthony Shivakumar
9th Jun 2026
Positional Encoding: Teaching Transformers Where To Look

Positional Encoding: Teaching Transformers Where To Look

attention C-Kernel-Engine machine learning positional encoding RoPE transformers 25 min read
Lab note Companion post to the Positional Encoding carousel. Previously: LayerNorm And RMSNorm: Stabilizing The Signal. Transformers are brilliant at reading an entire sequence in parallel, but that strength hides a structural weakness. If every token enters self-attention at the same time, the architecture does not automatically know which token came first, which came last, or which...
AS
Anthony Shivakumar
8th Jun 2026

LayerNorm And RMSNorm: Stabilizing The Signal

C-Kernel-Engine LayerNorm machine learning normalization RMSNorm transformers 20 min read
Lab note Companion post to the LayerNorm & RMSNorm carousel. Watch the companion video: Why LayerNorm and RMSNorm Matter in a C LLM Runtime. Previously: Activation Functions: The Nonlinearity Inside Neural Networks. The previous post was about the nonlinearities that bend a transformer into something expressive. This sequel is about the quieter operation that keeps those nonlinear...
AS
Anthony Shivakumar
7th Jun 2026

Activation Functions: The Nonlinearity Inside Neural Networks

activation functions backpropagation C-Kernel-Engine machine learning transformers 21 min read
Lab note Companion post to the Activation Functions carousel. Previously: Softmax: The Probability Engine. The previous Softmax post ended with a strange contrast. Softmax was beautifully smooth, but its Jacobian was dense, global, and a little expensive. This sequel walks in the other direction. Activation functions are local, element-wise, and deceptively simple, yet they are the ...
AS
Anthony Shivakumar
6th Jun 2026

Softmax: The Probability Engine

attention backpropagation C-Kernel-Engine machine learning softmax transformers 25 min read
Lab note Companion post to the Softmax carousel. Previously: Matrix Wx+b: From Scalars To Transformers. The previous post was about the moment a scalar weighted sum grew into a matrix multiply. This post picks up exactly where that one leaves off. Once a transformer has produced a row of scores, logits, or affinities, it still needs one more operation before those numbers can act...
AS
Anthony Shivakumar
5th Jun 2026
Matrix Wx+b: From Scalars To Transformers

Matrix Wx+b: From Scalars To Transformers

backpropagation C-Kernel-Engine GEMM machine learning matrix multiplication transformers 21 min read
Lab note Companion post to the matrix Wx+b carousel. Previously: scalar wx+b. Post 18 was the tiny version of the story. One input. One weight. One bias. One prediction. A clean scalar line: y = wx + b. This sequel is the scale-up. The algebra barely changes, but the objects do. Numbers become vectors. Vectors become matrices. A single prediction becomes a full...
AS
Anthony Shivakumar
4th Jun 2026
Backpropagation From wx+b: The Smallest Training Loop

Backpropagation From wx+b: The Smallest Training Loop

backpropagation c-kernel-engine chain rule deep learning derivatives 20 min read
Lab note This is the companion post to today's backprop-wxplusb carousel. I wanted a version with more room for the pictures, the algebra, and the engineering intuition. Previous post in this sequence This post builds directly on Derivatives And The Chain Rule: The Math Of Tiny Changes. That earlier piece explains why derivatives measure tiny changes. Here I use th...
AS
Anthony Shivakumar
3rd Jun 2026
Derivatives And The Chain Rule: The Math Of Tiny Changes

Derivatives And The Chain Rule: The Math Of Tiny Changes

backpropagation calculus chain rule control systems derivatives gradient descent robotics 25 min read
Lab note This post walks through the derivative and chain rule from first principles, with visualizations. It is the companion piece to my carousel post on the same topic. I needed this topic to stop feeling like ceremonial math notation. I needed it to feel like an engineering tool. Once I translated the derivative into the language of local change, and the chain rule into the l...
AS
Anthony Shivakumar
2nd Jun 2026
Why I Build Things From Scratch

Why I Build Things From Scratch

Antsand Builder Notes C Kernel Engine Ecological Monitoring Flight Controller Robotics 16 min read
Why do I keep building things from scratch? Antsand, C Kernel Engine, flight controllers, drones, robotics systems. The short answer is that I am contrarian, I hate bloat, and I cannot move forward mentally unless I can distill a system down to its primitives. This is not about pretending existing tools are useless. It is about how my brain works. I need to understand the raw ingredients, the...
AS
Anthony Shivakumar
31st May 2026

Training SVGs With C Kernel Engine: A Research Report

AI Training C Kernel Engine Curriculum Research SVG Tokenizer 83 min read
Main lesson The SVG experiments were not about making pretty pictures. They became a controlled laboratory for a harder lesson: training is a system design problem, not just an optimization problem. The result that made this clear was spec04. The model reached 100% renderability and 0% exactness. In plain language: it learned to emit something that looked like valid SVG, but it d...
AS
Anthony Shivakumar
31st May 2026
Hardening My Linux Engineering Workflow

Hardening My Linux Engineering Workflow

ai antsand c kernel engine kicad linux linuxutilities openems robotics workflow spice ai workflow ai hardening 14 min read
I am slowly moving more of my engineering life back into Linux. Not as a slogan. As a workflow. This is part two of my hardening series. Part one was Hardening Long Projects in the Age of AI. That post was about the discipline of staying with long projects, using AI without losing ownership, and turning old work into a system that can keep compounding. This post is the practical operati
AS
Anthony Shivakumar
29th May 2026
Quaternions, Axis-Angle, And Vector Rotation

Quaternions, Axis-Angle, And Vector Rotation

attitude math c drones quaternions robotics 13 min read
Quaternions have been one of those concepts I have spent years trying to understand, and I still find them annoying. I bought books on quaternions. I watched visual explanations. I went through robotics material, rigid-body dynamics material, and the usual this is actually simple explanations online. I understood pieces of it, but the concept never fully settled. It always felt like I was b
AS
Anthony Shivakumar
28th May 2026
Flight Controller for Drones

Flight Controller for Drones

antshiv-robotics control-systems drone flight-controller ins research robotics state-estimation 14 min read
Abstract / Executive Summary Antshiv Robotics is building a flight controller for drones from the math layer upward: attitude math, state estimation, dynamics, control systems, motor mixing, INS integration, thrust measurement, test rigs, visualization, and physical validation. A drone is not just motors, propellers, a frame, and a camera. A useful drone is a real-time control system. It has to e...
AS
Anthony Shivakumar
27th May 2026
What Is the C Kernel Engine?

What Is the C Kernel Engine?

ai-runtime backprop c-kernel-engine cpu research simd systems-programming 22 min read
Abstract / Executive Summary C Kernel Engine is an AI LLM inference and training engine optimized for CPUs. It takes model weights, model configuration, and computational graph templates, then stitches them into deterministic, hardware-targeted C code. The generated C is effectively a model-specific execution file: pointer wiring, kernel stitching logic, memory offsets, buffer planning, and calls...
AS
Anthony Shivakumar
26th May 2026
14 Ways React Brain Rot Infuriates Me and the Cost of SPA Overuse

14 Ways React Brain Rot Infuriates Me and the Cost of SPA Overuse

antsand architecture frontend hmvc react spa 23 min read
React brain rot is not just about React. It is about a way of thinking that makes developers forget what the browser already understands, what the server already knows, and what architecture was supposed to mean in the first place. I know the title is aggressive. I mean it that way. I have spent enough time dealing with over-engineered JavaScript systems, empty client-side shells, hydration lay...
AS
Anthony Shivakumar
25th May 2026
Is the Future of My Work Writing, Typing, Drawing, and Orchestrating?

Is the Future of My Work Writing, Typing, Drawing, and Orchestrating?

ai workflow antsand c kernel engine linux notes writing 12 min read
For the last few months, I have been noticing a strange shift in my work. I am still building software. I am still thinking about AI runtimes, Linux, C Kernel Engine, Antsand, content systems, drone math, control systems, and all the engineering projects I keep returning to in cycles. But the entry point into most of this work has changed. It is no longer always a code editor. Most days, the en...
AS
Anthony Shivakumar
24th May 2026

AI Is Teaching Everyone the Command Line. So Why Are We Still Ignoring Linux?

ai codex command line linux open source workflow 11 min read
The strange part of the current AI coding wave is this: almost every serious agent workflow is quietly becoming a Linux workflow, but Linux is still treated like the side door. OpenAI's Codex app page is a clean example. As of May 22, 2026, the page shows the desktop app available for macOS and Windows, while Linux users get a notification option. That is not some massive scandal. It is a product...
AS
Anthony Shivakumar
23rd May 2026

Your Job May Change. That Still Does Not Make Optionality Easy.

ai workflow antsand builders career linux optionality 18 min read
A lot of tech writing right now has the same shape: your job is going to change, AI is moving fast, you need optionality, become AI-native, maybe build a small software business, maybe consult, maybe package your knowledge, maybe make a few thousand dollars a month on the side. I agree with the direction. I do not agree with how easy it is often made to sound. This post is partly a re...
AS
Anthony Shivakumar
22nd May 2026

Are AI Agents Good for Your Brain?

ai agents deep work natural intelligence software engineering thinking 17 min read
A recurring criticism of AI coding agents is that they make people worse at the very skills needed to use them well. Cal Newport recently discussed this through the lens of agentic coding, cognitive atrophy, and deep work. I think there is a lot of truth in that warning. But I do not think the useful conclusion is do not use AI. That feels too blunt. It sounds a bit like sa
AS
Anthony Shivakumar
21st May 2026

Qwen3 From a C Runtime Perspective

ai runtime c kernel engine llm inference qwen3 systems programming 13 min read
Qwen3 is not just a model name inside C Kernel Engine. It is a concrete runtime target: a GGUF file, a model configuration, a set of tensor shapes, a generated C runtime, a packed weight blob, a shared library, an IR report, and a profiling surface. This post is for people who want to understand what actually runs when a modern LLM leaves the framework layer and becomes a CPU run...
AS
Anthony Shivakumar
20th May 2026

HTML Was Always the Interface. SVG Was Always the Diagram.

ai workflow html shivasnotes svg systems writing 7 min read
HTML was always an interface. AI just made that obvious again. I keep seeing people rediscover HTML as if it is a new invention. The new framing is usually something like: Markdown is no longer enough, HTML is becoming the better format for AI plans, specs, design systems, dashboards, and interactive artifacts. I agree with the direction. I just find the surprise ...
AS
Anthony Shivakumar
20th May 2026

Hardening Long Projects in the Age of AI

ai hardening antsand c-kernel-engine content systems syndication thinking web development 17 min read
Images generated by chatGPTI have been thinking a lot about hardening lately, especially with Antsand. Not hardening in the dramatic cybersecurity movie sense. I mean the boring kind of hardening. The kind where you go back to something you built years ago and make it less fragile. You fix the small UI bug. You clean up the ugly workflow. You upgrade the old part. You make the...
AS
Anthony Shivakumar
15th May 2026

Why I Replaced QuickBooks with Antsand — and Why I Think AI + Open Source Changes the Software Subscription Game

thinking ai workflow 13 min read
Source: Image generated by chatGPTThe Code Got Cheaper. The Infrastructure Didnt. For years, I paid for software subscriptions because that was simply how things worked. You needed invoicing, so you paid for accounting software. You needed ecommerce, so you looked at Shopify. You needed dashboards, so you paid for another SaaS tool. You needed a portfolio
AS
Anthony Shivakumar
6th May 2026

I Think Like a Compiler - But not in the way you think.

ai workflow thinking 6 min read
Over the years I have worked on a few personal projects, and I generally work on them long term (for years). Antsand is one of them. A flight controller is another. C-Kernel-Engine, which started as C-Transformer, is another. They look like different projects from the outside. One is a website and application builder. One is closer to embedded and control systems. One i...
AS
Anthony Shivakumar
30th Apr 2026

Why I Stopped Getting High on the Newer AI Models (And Why My Strategic Bet Is Still Consistent: CPUs, Smaller Models, and Less Compute Will Win)

ai workflow c-kernel-engine 14 min read
AS
Anthony Shivakumar
21st Apr 2026

My two-tier A.I workflow: frontier thinks, MiniMax (open weights) does the heavy lifting

ai workflow 5 min read
Everyone assumes you need the most expensive model to write good code. They are wrong. I have spent the last year building a CPU inference engine from scratchno PyTorch, no TensorFlow, just C and x86 intrinsics. Along the way I learned something: the model that understands you is not the same model that should write your code.
AS
Anthony Shivakumar
5th Feb 2026

Why I’m Doubling Down on C in 2026

ai workflow 4 min read
It's 2026, and the hype around memory safety is deafening. The industry consensus seems to be that C and C++ are archaic, "unsafe" languages that we need to abandon immediately. There is a growing chorus pinpointing that the majority of CVEs (Common Vulnerabilities and Exposures, the standard system for cataloging publicly known security flaws), from databases to the Linux kernel and even Git, st...
AS
Anthony Shivakumar
2nd Jan 2026

The Great Untangling: Why I Ditched Vue, Node, and Microservices for Pure JS, PHP, and AI

web development antsand 7 min read
I have been developing Antsand since 2014. It is my digital garden, a sophisticated personal project that generates federated, static websites, including the blog you are reading right now.Eleven years is an eternity in software development. Antsand has survived multiple eras of "the next big thing." By 2021, the application had matured into a complex beast powered by Vue 2 on the front end and a ...
AS
Anthony Shivakumar
31st Dec 2025

Unimporting PyTorch: How Constraint and Curiosity Built a C Kernel Engine

4 min read
In a world where everyone is rushing to build the next high-level autonomous agent or wrap an API in a nice UI, I decided to go in the opposite direction. I wanted to go deep. I wanted to see the "ghost in the machine."My journey started with a project called C-Transformer, where I wrote GPT-2 from scratch in C with the help of AI. That experience was transformative. Now, armed with the mistakes a...
AS
Anthony Shivakumar
23rd Dec 2025

Archived Personal Posts

Older writing, daily notes, business posts, year-end notes, and personal archives.

The 3rd Week of January

personal 3 min read
17 Jan 2021 by Anthony ShivakumarThis past week or so I have been doing good energy-wise. One being, I can get up very early. Anywhere between 4:00 am and 5:00 am. I do not put an alarm. I get up organically. I love it. After I get up, go to the washroom and wash up, I then sit and do the Wim Hof breathing exercise. It is a great way to start the day. A bit of deep breathing, yoga, and some medita...
AS
Anthony Shivakumar
21st May 2021

Client work and system identification

personal 1 min read
On Monday I was working on a bit of client work and on drone tech. I woke up at 5:00am and started to do week 2 of the wim hof breathing. It is a good start to my morning. Get my lungs moving and helps set my mind for the day ahead.As mentioned, mostly client work was the goal of the day. Monday and Tuesdays will be focused more on client work and ANTSAND, while the rest of the week will be focuse...
AS
Anthony Shivakumar
13th Jan 2021

Understaning the Kalman Filter

personal 3 min read
I am writing my Saturday and Sunday Journal together and a day later.Saturday the 9thOn Saturday the 9th, I got up arund 6:30. I haev not done the Wim hof Breathing ever since I did my afternoon run and got a bad eye and head ache. I just wanted to take a day or two off from breathing. Which in the morning allowed me to spend time working. I had to reply to a friend which I did. It took about a
AS
Anthony Shivakumar
11th Jan 2021
Headache and eye hurt

Headache and eye hurt

personal 2 min read
Today started off well. Got up at 4:45 and started to do my Wim Hof breathing. Then I got to work on the sensor fushion algorithm. I had breakfast at 7:45am. Around 8:30 am I had a shower. I ended it with 1min of cold water. It felt good. I still believe I have the groin cycst. The cold shower helped a bit.After which I had a meeting at 9:30 am and again go to work on the sensor algorithm. My g
AS
Anthony Shivakumar
7th Jan 2021

The importance of priority #1. What is ANTSAND and why is it being built?

Business personal 7 min read
ANTSAND first started as my personal dairy to keep track of my life. At one point in time, I did not wanted to use any Social media sites. I wanted to only use the one I created. I think the creator in me thought, if I can build one, I will build one. Why do I need to use other products. This idea has still not completely grown out of me. For the most part I am vey much a maker.I have been working...
AS
Anthony Shivakumar
6th Jan 2021
Progress on Drones

Progress on Drones

personal 2 min read
I did not write yesterday's journal. Today and yesterday I woke up at 430 am. This is so that I can squeeze in the Wim Hof Method in the morning. I want to get into the practice of breathing, meditating yoga, and perhaps even cold showers. My eating habits too, have been improving. Though today I did skip lunch. I had a slight headache and my left eyes were hurting. Plus I woke up at 4:30 am so I ...
AS
Anthony Shivakumar
6th Jan 2021

3rd day of the year

personal 2 min read
Today, I got up at 5:00. Started to do the wim hof method week 1. It is going good. I feel great after each session. I want to get up earlier, perhaps at 4:30a.m so that I can get a head start on the meditation, breathing and yoga.At 7:30 a.m I cooked Uppma for breakfast. Eating breakfast in the morning is a wonderful routine. It help me keep check of the time. This way I am aware what I am doi
AS
Anthony Shivakumar
4th Jan 2021

The 2nd day of the year

personal 1 min read
Today i woke up at 5:00 am. around 5:30 am or so I started to do the Wim Hof method. The breathing exercise, yoga and meditation. At 7 am I had to go out to get some bread for my breakfast. I then came home and prepared breakfast.For breakfast I prepared a sandwich, avocado, roasted chic peas and sprouts. With the sandwich I also had leftover butternut squash soup. It was a good healthy breakfast....
AS
Anthony Shivakumar
3rd Jan 2021

1st Jan 2021

personal 3 min read
I am not big into the New Year celebration thing. It is just another day. Every day is kinda a new year. So, it is just a matter of perspective. Nevertheless, the date change does make a psychological impact. the 1st of the month, a different or new year. It is in these times we tend to set goals, resolutions, change things up for the better, make commitments, and try to keep up. I am no differ
AS
Anthony Shivakumar
2nd Jan 2021

A cooking day

personal 1 min read
Woke up around 6:00 am. and worked on making a proper meal plan. We then went for gorcery shopping at 8:00 am. After we came back I made myself brunch while washing some of the fruits we just bought. I did not get much work done today. I did take a short afternoon nap. I may need to drink coffeee to keep my self awake. After I woke up, I prepared to cook the butternut squash. While cooking I did m...
AS
Anthony Shivakumar
31st Dec 2020
Working on ANTSAND

Working on ANTSAND

personal 2 min read
Today is ANTSAND day. Monday and Tuesdays is where I will dedicate my time on ANTSAND. I got up today around at 6:00am. Went to the toilet, brushed my teeth and got to work. Around 9:45 am or so, I did my TACFIT moderate intensity workout. It is always good to follow and stick to my fitness plan. In the coming new years, I will want to make fitness and my eating habits set. No more burping, fartin...
AS
Anthony Shivakumar
30th Dec 2020

A lazy day

personal 1 min read
Today, I got up early and worked on some client work. I felt very bloated in the morning. A lot of burping. I also sent a mail to a potential co-founder on starthawk. I most likely will need to look for a co-founder for ANTSAND. Will need someone who can take care of sales and marketing.We then went for a walk followed by a run round the park. The distance covered was approx. 2.7 km. I beleive
AS
Anthony Shivakumar
29th Dec 2020
Root Vegetables

Root Vegetables

personal 2 min read
Today, the 27th of December (Sunday) was a normal day. Got up around 7. We did our recycling before I joined my mastermind. The mastermind session was good. Chill, relaxed and we just spoke on few different topics. One of the books that was recommended was Siddhartha y Herman Hesse. Another interesting blog that was mentioned was neilonsoftware.com .After mastermind, I did feel a bit lazy an
AS
Anthony Shivakumar
28th Dec 2020

Getting the acclerometer working

personal 1 min read
Today, once again I got up early and started to work on getting the accelerometer working. I did start to get it working. Had a meeting with a friend that is likely to collaborate with me to make drones. After the meeting, we went for a walk. I had my mastermind meeting today too. I only spent an hour in the meeting. don't want to spend more than 3 hours a day on meetings.After which I did m
AS
Anthony Shivakumar
7th Dec 2020
I2C and learn how to troubleshoot

I2C and learn how to troubleshoot

personal 1 min read
Today is hardware day.. Woke up early and got working on interfacing the gyroscope and accelerometer. The whole morning went trying to get I2C working. The signal were just not right. It took me the whole day to realize that there was a connection isssue. Nevertheless, I got it working. A clean signal like this always feels good.Healthwise, I am feeling a lot better. No more pain as such. I did do...
AS
Anthony Shivakumar
5th Dec 2020

Learning Kalman Filtering ...

personal 1 min read
Today was a lazy. Woke up a bit late, did not do any exercise and just not productive as such. Towards the evening I did spend some time learning how to use Kalman Filtering for attitude control of a quadcopter. Tomorrow, I will try to get the accelerometer and gyroscope working and see if I can start to apply the Kalman Filter.My stomach still has the left side discomfort. I did go to the toilet ...
AS
Anthony Shivakumar
4th Dec 2020

Recovering ... but bloated

personal 1 min read
Today, I did not want to do too much. So I spent time studying some Machine Learning Algorithims. Pretty much the whole went in learning.My health is better, though I felt really bloated after dinner. I ate a decent size meal, but the bloating is a bit concerning. Hopefully the tablets I take Ilaxatives) will help relieve some of these issues.Tomorrow, I might spend more time on ML. Perhaps wor
AS
Anthony Shivakumar
3rd Dec 2020

Recovering ...

personal 1 min read
Today, I was feeling much better. I went to the doctor and they gave me a few tablets. If the problem still continues after 2-3 weeks then I need to go back. I have got most of my appetite back. I was able to eat my salmon, kale, yoghurt, naan, sprouts and avocado for lunch.I plan to now work, 3 days on hardware and 4 days on software. The 4 days of software will include working on A.I, machine
AS
Anthony Shivakumar
2nd Dec 2020

Little Tension and a christmas tree

personal 2 min read
Today, I did not sleep too well. I work up at around 3:30 a.m. due to burping and farting. I did drink the prune juice yesterday. It might have been the cause of my discomfort. My fiance could not bear the smell, so she slept in the living room. After an hour or so, I did got to the toilet and was able to pass motion. The prune juice helped. When I got back to bed, I did not want to start worki
AS
Anthony Shivakumar
30th Nov 2020

let the progress begin ...

personal 2 min read
Alright, today was just a normal day. I work up at 6:30 am. I did pass motion, so that was good. Still constipated though. Not sure what the issue is. Hope it is not something too critical.We went for a morning walk as it was bright and sunny. A walk always helps. I might need to walk more often to get my bowel movements going. Either in the morning on after lunch.Today, was also the last day o
AS
Anthony Shivakumar
29th Nov 2020

Another slow day

personal 1 min read
Embedded system programming is tedious. Sometimes things work fast and quickly, sometimes they just take time. My progress this month has been very very slow. I have switched from working on the nrf24ap2e to the nrf24l01+. The latter is easier to configure. I want to get the radio working by the end of the month. .. Hopefully I can get something working soon.My fitness is going well. I have com
AS
Anthony Shivakumar
28th Nov 2020

The day of ups and downs

personal 2 min read
Oh, today was an exhausting day. Not physically, but emotionally.My day started like any other day. Woke up early, passed motion, which is good. Not too constipated. Had a shower and got to work. Today is solder day. Which is, the day to solder another radio and get the two radios talking. Unfortunately, the soldering did not go as well as I planned. In 2014, I had bought enough components to make...
AS
Anthony Shivakumar
27th Nov 2020

Let us get moving

personal 1 min read
Today, once again i started the day early. A bit constipated. Hopefully nothing major. I might have to do more movement exercises. If it persists for a few more days or a week, I will have to go see a doctor.Other than that, I got most of the ANT+ radio config working. I was not able to check over the air signals. I will need to solder a new radio tomorrow or by the end of the week. I also was abl...
AS
Anthony Shivakumar
26th Nov 2020

More work .. but progressing

personal 1 min read
Today, once again I got up early, around 5:30 a.m. Had a shower and got to work. My goal for today was to progress more on the radio. I want to get it to start interfacing. Te protocol is a bit complicated. I hope to get it working by the end of the month.I also studied a bit from the course "Sensor Fusion and Non-linear Filtering for Automotive Systems" on Edx. It seems to be a decent course. I w...
AS
Anthony Shivakumar
25th Nov 2020

Drone Specification ...

personal 2 min read
Today, was just another day. Got up a bit late, around 6:30 a.m. I did a bit of the machine learning course in the morning. After which, I did my workout. Before my workout, I was once again browsing the different courses on Coursera / Edx related to image processing, sensor fusioh etc. It is easy to get carried forward in designing a very big system. To stop my self from doing that, I spent ti
AS
Anthony Shivakumar
24th Nov 2020

Getting the radio to work ...

personal 1 min read
Today, once again I got up early. Not too early, around 6:30 a.m. My plan was to work more on the radio and get it interfacing with the microcontroller. I am progressing well in this regard. Hopefully soon, I will be able to send data over the air. This will be a good achievement.I also had our mastermind session today, The discussion were good. We talked about business, ideas, philosophy and r
AS
Anthony Shivakumar
23rd Nov 2020

Another Day ...

personal 2 min read
Today, once again I got up a bit early, at 6:30 a.m. Had a shower and worked a bit on ANTSAND. There are bugs in the app, and I plan to work on it frequently. One thing I have realized today, regarding the making of the drone, is to not focus on theoretical stuff anymore. The only theory I can work on is on A.I. I will only get back to theory once I have a drone that is flying and working. It is i...
AS
Anthony Shivakumar
22nd Nov 2020
Let's get the drones sketched

Let's get the drones sketched

personal 3 min read
Today, once again, I got up early, around 5:30 am, had a shower, and got down to work. In the morning, I was working on interfacing the radio with the micro-controller. I got most of the device driver working. Next, I will need to send some ANT+ commands and see if it will transmit the messages over the air. After which, I did my Tacfit Commando. Today, was a high-intensity day. I did push myself ...
AS
Anthony Shivakumar
21st Nov 2020
A dumb A.I.

A dumb A.I.

personal 3 min read
Today, my day did not start at 5:30 am. It started at 2:30 am when a funny smell polluted our room. We woke up from the smell as it smelt like burnt plastic. We were not sure if it was caused by something in-house or it was coming from outside. We went out to check and the smell was stronger outside. There was nothing we could do, so we closed all the windows and went back to sleep.Sleep interrupt...
AS
Anthony Shivakumar
20th Nov 2020
Getting Closer

Getting Closer

personal 1 min read
Once again, today I got up early, had a shower and got straight to work. The agenda for today was to work on the radio fro 6:00am to 10:00 am. I did stick to my plan. I was able to progress further with the radio. Hopefylly by the weekend, I can get it to work properly.After working on the Radio, at 10:30 or so I did my Tacfit Commando. The exercies, the morning routine and the evening routines
AS
Anthony Shivakumar
19th Nov 2020

Getting the radio working - Work in progress

personal 3 min read
Today, once again I got up early at 5:30am, had a shower and got straight to work on interfacing with the radio. Embedded systems and interfacing is not particularily difficult, but it does cosume a lot of time. Espcially if you are trying to get something working with limited resources. When it comes to these types of things, the manufactuere should provide sample code. In this case, little to no...
AS
Anthony Shivakumar
18th Nov 2020
Let the training Begin

Let the training Begin

personal 4 min read
My morning routine of getting up early is going well. I got up at 5:30 am, had a shower, and got straight to solving the backpropagation algorithm. Surely, in the mornings my mind reaches a new level of concentration and focus. I got the assignment working in an hour. After which I did my Tacfit commando. Today was the high-intensity day. I believe I pushed myself quite hard. I reached a heart rat...
AS
Anthony Shivakumar
17th Nov 2020
Back Propogation

Back Propogation

personal 1 min read
Today, once again, I woke up at 5:30 am, had a shower, and got straight to work. Today I wanted to get the back-propagation algorithm of a neural network to work. Unfortunately, I am still struggling to get it to work. What I did today?I woke up earlyI did my Tacfit Commando exercisseI went for a walkI took a good afternoon nap.I worked on Week 5 of the Machine learning course by Andrew Ng. I am ...
AS
Anthony Shivakumar
16th Nov 2020
Neural Networks and a so so day ...

Neural Networks and a so so day ...

personal 3 min read
Today, once again I got up early, around 5:30 am, had a shower, and got down to work on completing the neural network chapter from the course Machine Learning on Coursera by Andrew Ng. I am now in chapter 5 and need to finish the backpropagation chapter. Once I get the backpropagation to work, I will start to train the neural network to create websites. At least, this will be the 1st step towards ...
AS
Anthony Shivakumar
14th Nov 2020
The Radio

The Radio

personal 5 min read
Today, once again, I got up early, around 5:30 a.m. I had a shower and got straight to work. My goal for today was to get as much client work done by 10:00 am, do a workout, and start working on interfacing the radio module. I had a bit of pending client work, so I tried to get as much done. At 10:00 a.m, it was a hard stop. This meant, even though I did not complete the client work, I had to stop...
AS
Anthony Shivakumar
14th Nov 2020
Client work

Client work

personal 2 min read
Today was client day. I got up early at 5:00am, had a shower and got to work on client work. I am working on a website for a clinic. The design needed a few elements that were not readily available in ANTSAND. so I had to progam a few features in. I worked for a few hours before I had a call with my business partner. After which I did my cycle 3 of tacfit commando. The fitness side of things is go...
AS
Anthony Shivakumar
13th Nov 2020
Machine Learning progress

Machine Learning progress

personal 3 min read
Today seemed to be a good day. I got up early, around 5:30 am, brushed my teeth, had a shower, and got started working on the machine learning course by Andrew Ng. I wanted to complete the logistic regression chapter and get started with a neural network. I wanted to end the day implementing my neural network to auto-create websites. Unfortunately, I procrastinated a bit. Plus, it does take time t...
AS
Anthony Shivakumar
12th Nov 2020
The Starry night

The Starry night

personal 3 min read
Today, I got up a bit late. Around 6:30a.m. The reason being I slept a bit too early last night and had to get up in the middle of the night. The sleep interruption offset my sleeping schedule by an hour. After getting up, had a shower and got back to work. I posted my app on product hunt and submitted ANTSAND to app sumo. A bit of marketing. Then, I did my tacit commando. After which I needed to ...
AS
Anthony Shivakumar
11th Nov 2020
logistic regression

logistic regression

personal 1 min read
Today was a slow day. I did get up early around 5:30, had a shower and got to work. I completed a few client work in the morning. I also did my Tacfit commando workout. After which I studied logistic regression from a machine learning course taught by Andrew Ng from Coursera. Around noon I cooked some fish curry and ate the same for dinner. Noon time I was once again studying the course. Tomorr
AS
Anthony Shivakumar
10th Nov 2020
The pivot

The pivot

personal 2 min read
Today was a good day. I got up early, had a shower, worked a bit on ANTSAND. Did my Tacfit Commando (high-intensity day). Then we went for a walk around the nearby park. The walk was half-hour long. After this, I had my mastermind meeting from 10:00 am to 12:00 pm. I needed to install OpenCV to do some image processing/ computer vision work. I had a few issues trying to install it. Once I got it t...
AS
Anthony Shivakumar
9th Nov 2020
Headaches and a dud day

Headaches and a dud day

personal 2 min read
Today was a slow start. Got up around 7 a.m. We went grocery shopping around 8:30 a.m. As the covid cases are rising, we were preparing to stock up on some food in case there will be another lockdown. After coming back from grocery shopping, I had a slight headache. I took a nap before having a call with one of my mastermind friends. We talked about drones and more about the ANTSAND app and how he...
AS
Anthony Shivakumar
8th Nov 2020
the Dilemma

the Dilemma

personal 2 min read
Today, once again I started the day early. Had a shower and tried to figure out what I want to do today. I wanted to get started doing some machine learning A.I. course. I also needed to work on getting the infrastructure in place. Which is the ability to get data, process data, train the A.I., and then deploy the A.I. to an application. There is a bit of backend code that is needed to be done. Th...
AS
Anthony Shivakumar
7th Nov 2020
Just another day

Just another day

personal 2 min read
Today, once again I started the day by getting up early, around 5:00 a.m. Had a shower and got down to work on client work. I needed to add some animation on a client website. Since all my clients website are now directly powered by ANTSAND, I had to fix a feature in ANTSAND itself. I got it working so that is good.Then around8:30 am I did my conditioning exercise. Day 5 of my program. Today was a...
AS
Anthony Shivakumar
6th Nov 2020
A sore body and a semi-productive day

A sore body and a semi-productive day

personal 3 min read
My morning routine is going great. I got up at 5:30 a.m, had a shower, and started to get down to work on antsand. At 7:00 am, I had a consulting call with one of my clients. At 8:15, the call ended and I got down to do my high-intensity workout. The 1st cycle of mission one is complete. Six more to go. The table below shows my performance.Day -4 Mission 1 Tacfit Commando - High IntensityExercise1...
AS
Anthony Shivakumar
5th Nov 2020
Let the exercise begin

Let the exercise begin

personal 4 min read
Today, I started the day pretty well. I got up at 5 a.m., had a shower, and got right down to work on ANTSAND. Today's goal was to fix SSL or auto-configure websites for security using LetsEncrypt. Honestly, all my design ideas turned out to be fruitless. Which is to say, I would need to come back to this at a later date and figure out how to auto-configure websites for security. One of the reason...
AS
Anthony Shivakumar
3rd Nov 2020
Day 2 of my Journaling

Day 2 of my Journaling

personal 2 min read
Today is my 2nd day of writing. I got up early, around 5:00 am. Daylight savings did help me to get up early. Had a shower and was ready to get started programming. Being the 1st working day of the month, I sent invoices to my clients. Today, I had to work on the form section of ANTSAND. Finish up with the "don't break the chain rule" feature. While doing so, I got a chance to refactor some of my ...
AS
Anthony Shivakumar
3rd Nov 2020
Blog writing and habit tracking

Blog writing and habit tracking

personal 3 min read
Today I have started a new blog called shivasnotes.com. This blog is to help me keep track of my journaling, habits, and accountability. I have wanted to do this for a while, but I kept coming up with excuses. Nevertheless, I am happy I got started.In this blog, I plan to write on my challenges like the 30-day challenge, rant on random topics like productivity, health, fitness, hobbies, mindsets, ...
AS
Anthony Shivakumar
2nd Nov 2020
39+ mental tools I use to make better decisions

39+ mental tools I use to make better decisions

mental models personal 16 min read
Are you looking to start a company, make a drastic change in your life or are you stepping into the unknown? There are forces of nature that are there to help and guide you if you look for them. It can get scary, fearful, and very daunting. As a result, I have compiled a list of things that will guide me even in the darkest moments of life and business.   This is a list of belief that I use as a
AS
Anthony Shivakumar
1st Oct 2018
13 things I learnt after doing the 10-week wim-hof method

13 things I learnt after doing the 10-week wim-hof method

lifestyle personal 14 min read
Do you get a migraine or sinus and lose a full days worth of productivity? You think yoga is for old people or it is too boring to do it? You tried meditation, and think you are better off going to sleep than sitting like a fool? Or even the thought of cold showers frightens you, why would anyone do it?  Let me tell you a little about myself. I have lived with headaches like a migraine an
AS
Anthony Shivakumar
2nd Apr 2017

Subscribe

Get my rants delivered to your inbox

I will send new posts as and when I write. No fixed cadence, just engineering notes, rants, and things I am thinking through.

ShivasNotes

Independent notes on software, systems, AI workflows, robotics, and building Antsand in public.

Read

Support