Trip to Southern Utah
OpenAI's mid-year break was a chance to fly to Las Vegas, drive into southern Utah, and hike around Zion, Escalante, and Bryce Canyon.
Follow Alex Leung's latest essays on software and AI tools, technical book notes, experiment write-ups, and personal reflections.
OpenAI's mid-year break was a chance to fly to Las Vegas, drive into southern Utah, and hike around Zion, Escalante, and Bryce Canyon.
My coding-agent sessions are more expensive now. The useful spend is the part that turns mistakes into better tests, graders, prompts, and checks.
My first week in San Francisco: paperwork, an unfurnished apartment, two cats, Bay Trail runs, and waiting for furniture.
Building frontend-only tools for load flow and Mandelbrot zooming gave me concrete ways to inspect older technical models.
A concrete way to understand dropout in deep learning: sampled subnetworks with shared weights, standing in for a much more expensive ensemble.
Notes on the 11-inch M3 iPad Air for reading, handwriting, and remote access without turning it into a laptop replacement.
I replaced scattered responsive-image conventions in a Next.js static site with one generated manifest for variants, dimensions, and runtime lookup.
AI-assisted prototypes make small workflow ideas cheap to test before they compete for dedicated engineering time.
How Codex made small website edits easier to make from a phone, while Sora still feels more useful for exploratory visuals than finished work.
Chapter 6 separates representational capacity, parameter efficiency, and learnability—and shows why depth changes scaling, not just expressiveness.
Part I of Goodfellow, Bengio, and Courville works best as shared vocabulary for later chapters, with proof details still worth supplementing.
How my AI-assisted coding workflow shifted from quick snippets to clearer briefs, review checkpoints, and build/lint/test verification.
How repo-backed Markdown becomes static HTML without a CMS, database, or runtime admin surface.