About — field notes

Hariom Lohar

Self-taught from India, rebuilding intelligence from scratch — Harvard CS50P 2026, 8h a day, committed in public.

01 — About

Field notes

Who does the work
Open to work
Portrait of Hariom Lohar
fig. 00 — hariom, thinkingIndia · IST

Self-taught from India, rebuilding intelligence from scratch — one proof, one commit at a time.

I finished 12th grade and chose the longer road — no bootcamp, no shortcut. The day goes into first principles: mathematics from axioms, derivatives by hand, then neural networks built the same way — a Value graph, backprop and gradient descent written in NumPy before touching a framework.

micrograd_hk is that work as a package you can pip install. Now: CNNs, Transformers and PyTorch. All in public, every day.

Location
India · IST
Focus
AGI from first principles
Log
Day — of —
Open to
Freelance & collabs
02 — How I work

Three rules

No shortcuts
01

Derive before you import

Do not use what you cannot derive. Math from axioms first, then architectures by hand in NumPy.

02

Eight hours, every day

One deep-work block, documented in AGI_Research so the log stays honest. Committed daily.

03

Build in public

Errors, proofs and small wins are all commits. The notebook stays open on GitHub.

Ready when you are

Let’s build something that lasts.

Backends that stay up, apps that feel native, and search over your data — or join SIGMOID and build in public, one log at a time.

Start a project → Join SIGMOID ↗ Usually replies < 24h · IST