🌄🌱👑’s 🌌
ai APFS applescript automation backpropagation cadence claude cross-entropy data recovery debugging deep learning digital design email embeddings ic language-model latex linux liveness-analysis llm mac machine learning macos memory microsoft office network notes on-chip-training physical-design postfix programming python pytorch research rtl self-hosting sram ssh sysadmin Time Machine transformer verilog vt wordpress
-
How to save an APFS HDD
A large APFS drive stopped mounting, First Aid gave up, and the data existed nowhere else. Five days, two repairs, one wrong turn that corrupted it again, and the tooling we wrote along the way.
-
Skipping AppleScript to search Apple Mail fast
AppleScript’s whose filters on Mail.app aren’t index-accelerated by anything, so they crawl on a big mailbox and can wedge Mail’s automation bridge entirely. Mail already keeps its own indexed SQLite database on disk. Read that instead.
-
Fixing herdr machine add: lost connection to server
herdr 0.9.0’s multi-machine support failed with a vague ‘lost connection to server’ between two of my three Macs. The real error was hiding one flag away: herdr enforces strict host key checking itself, and overrides whatever your SSH config says about it.
-
Minimal setup for inter AI agent communication with herdr
herdr has no network layer of its own, just a local socket. Turns out that’s enough: SSH forwarding gets two agents on different machines talking both ways, no server required.
-
Where Facebook hides the permalink
Five ways to grab a Facebook post’s link that all fail, the one place the link is actually sitting, and how to make sure you never capture the wrong one.
-
Your Server Has Been Trying to Tell You Something
A compute box with no mail stack, taught to reach real inboxes through a mailbox we already owned. Plus the parts every send-only Postfix tutorial skips, and the failure that shows up only once it works.
-
Torch Visualized: The Operations
Fifty PyTorch tensor operations, one 3D figure each: input and output superimposed at a shared origin, with the runnable call and the shape change on every page.
-
Train a Transformer on Silicon: #3 The Memory Is the Chip
v0’s die was 85% SRAM. H01 packs the flat memory map with liveness analysis and an early-SGD reschedule — 145,952 words down to 90,896, the die from 6.99 to 4.55 mm², 35% smaller — without changing one logic gate. The compute was never the problem; the memory was.
-
Train a Transformer on Silicon: #2 A Decoder Is Just an Encoder with a Mask
v0 is done: a nanoGPT-faithful decoder layer that trains itself — forward, backprop, and SGD update — bit-exact against a golden model and taken to a clean 45 nm layout. The compute fit in 0.117 mm² of logic; the memory took 85% of the die.
-
Train a Transformer on Silicon: #1 Backprop on a Chip
Most AI chips run a model someone else trained; this one does the training itself — forward pass, backpropagation, and weight update, in fixed-point RTL, all the way down to a 45 nm layout.
-
Publication-Quality Chip Layout Figures from Innovus, Headlessly
Innovus has no vector export and its GUI screenshots don’t scale. Here’s a fully scripted pipeline: a headless 16,000-pixel render, block coordinates pulled from the P&R database, a zero-residual pixel-to-micron calibration, and a matplotlib wrapper that turns it all into a self-describing PDF/SVG figure.
-
Benchmarking 17 AI Models on Razavi’s Analog Design Questions
I re-ran Behzad Razavi’s ‘Analog Mind’ LLM experiments across 17 model configurations, with a controlled anonymized grader and ngspice as the referee. The methodology moved scores as much as the models did.
-
One Prompt, One Complete IEEE Transactions Project with Claude Code
A single copy-pasteable prompt that makes Claude Code scaffold a complete IEEE Transactions LaTeX project: main manuscript, S-numbered supplementary materials, a shared author file, and a full revision workflow – with no dependencies beyond a TeX distribution and make.
-
Train a Transformer on Silicon: #0 The Genesis
Start here — the series hub A short intro to a series where I build a chip that trains a transformer — and document the whole thing, mistakes included. What this is I’m building a digital chip that trains a transformer on-chip — not just runs it, but actually learns: forward pass, backpropagation, and weight…
Got any book recommendations?