BUILD

Things from the workshop. Showing thinking, not just output.

01 · 2026
BYOB Studio

Ship a full web app from one prompt — inspectable SvelteKit you own.

Why: Generated demos are disposable. I wanted generation that stays editable, testable, deployable.

Learned: Inspectability beats magic. Version rollback and git diffs matter more than generation speed.

[site →]
02 · 2026
che4os

My personal operating system. Plain surface, deep rabbit hole.

Why: A portfolio answers recruiters. I wanted a corner of the internet that answers curiosity.

Learned: Restraint is a feature. Static content, dynamic atmosphere.

03 · 2023
Podcast Ad Detection

Unsupervised detection of ads in podcasts, straight from audio.

Why: Ads break flow. Skipping them should not need labeled data.

Learned: Unsupervised structure-finding goes further than expected on audio.

[source →]
04 · 2022
Accent-Preserving Voice Cloning

One-shot voice cloning that preserves the speaker accent via accent embeddings.

Why: Cloning that flattens accent erases identity. Accent is content.

Learned: Disentangling speaker, content, and accent in one shot is genuinely hard.

[source →]
05 · 2022
Disentangling Emotions in Speech (β-VAE)

Unsupervised disentangled representations of emotion in speech.

Why: Supervised emotion labels are noisy. Structure should emerge, not be imposed.

Learned: Beta-VAEs buy disentanglement at the cost of reconstruction. The tradeoff is the work.

[source →]
06 · 2021
Interactive Virtual Wall

Touch-based interactive wall via stereo camera and ROS.

Why: Rooms should be interfaces.

Learned: Calibration is everything. Demos live or die on setup robustness.

[source →]
07 · 2020
Whatsapp Chatbot (Seq2Seq + Attention)

A neural conversational interface over Whatsapp.

Why: Meet people where they already talk.

Learned: Old-school seq2seq fluidity is mostly a data problem.

[source →]
08 · 2019
Game Playing with Deep RL

DQN and variants trained to superhuman play on Flappy Bird and Daddy Long Legs.

Why: Nothing teaches RL like watching an agent go from flailing to superhuman.

Learned: Reward shaping and training stability dominate architecture choice.

[source →]