Hacker News: oakinnagbe

New comment by oakinnagbe in "Ponytail – make your AI agent think like the laziest senior dev in the room"

oakinnagbe — Mon, 15 Jun 2026 12:24:04 +0000

The repo is bigger than most of the code Ponytail would allow me to write.

New comment by oakinnagbe in "Exploring building a tiny FUSE filesystem"

oakinnagbe — Mon, 15 Jun 2026 12:19:21 +0000

If I have to ask whether something is AI-generated after reading 11 minutes of filesystem internals, that's probably a compliment to the writing.

New comment by oakinnagbe in "Exploring building a tiny FUSE filesystem"

oakinnagbe — Mon, 15 Jun 2026 12:19:03 +0000

The older I get, the more I appreciate posts that are basically I wanted to understand X, so I built a tiny version of it.

New comment by oakinnagbe in "The Birth and Death of JavaScript (2014)"

oakinnagbe — Sun, 14 Jun 2026 13:13:59 +0000

Every few years, we invent a better JavaScript. Then we transpile it to JavaScript.

New comment by oakinnagbe in "Beagle: Git, URIs and all the dirty words"

oakinnagbe — Sun, 14 Jun 2026 13:11:39 +0000

I admire any attempt to simplify Git. I'm less convinced that making it look like HTTP is the simplification people were asking for

New comment by oakinnagbe in "Trophic memory, deer, and a unique scientific object"

oakinnagbe — Sat, 13 Jun 2026 18:11:16 +0000

Fascinating read. Also a reminder that aesthetics and fire safety occasionally have very different priorities.

New comment by oakinnagbe in "Appreciating Exif"

oakinnagbe — Sat, 13 Jun 2026 18:07:05 +0000

Exif is technical debt in the most flattering sense. Messy, old, and still quietly useful decades later.

New comment by oakinnagbe in "The Future of Email"

oakinnagbe — Fri, 12 Jun 2026 10:59:24 +0000

We’re basically outsourcing email judgment to AI, then trying to compensate by strengthening SPF/DKIM. That feels like hardening the locks while handing out more master keys.

New comment by oakinnagbe in "An introduction to functional analysis for science and engineering"

oakinnagbe — Wed, 10 Jun 2026 14:06:07 +0000

That feels more like a selection effect than a property of the writing tool itself.

New comment by oakinnagbe in "An introduction to functional analysis for science and engineering"

oakinnagbe — Tue, 09 Jun 2026 13:51:45 +0000

Genuine question: does the writing tool matter at all here if the exposition is clear and mathematically correct? I’ve seen great notes written in Word, LaTeX, and even slides—quality seems independent of format.

New comment by oakinnagbe in "A Survey of Inlining Heuristics"

oakinnagbe — Tue, 09 Jun 2026 13:44:31 +0000

Really nice write-up. After reading through the survey, I’m curious if there’s any evidence that more complex heuristics (ML-based or multi-stage policies) actually outperform simpler budget + size + hotness models in production JITs, or if they mainly help at the margins.

New comment by oakinnagbe in "Tiny hackable CUDA language model implementation"

oakinnagbe — Mon, 08 Jun 2026 12:53:46 +0000

Nice implementation. Have you thought about supporting LoRA fine-tuning on top of this, or is the design too low-level for that kind of extension?

New comment by oakinnagbe in "Ask HN: What is your (AI) dev tech stack / workflow?"

oakinnagbe — Fri, 05 Jun 2026 17:53:47 +0000

At work I mostly use Codex, while for personal projects I've settled on OpenCode. The split is less about model quality and more about context. Work projects benefit from consistency and predictable workflows, whereas side projects are where I experiment with different models, prompts, and agent setups.

New comment by oakinnagbe in "Gov.uk has replaced Stripe with Dutch provider Adyen"

oakinnagbe — Fri, 05 Jun 2026 17:49:13 +0000

I'm curious whether this will materially reduce costs for local authorities or whether the benefits are primarily in expanding payment options.