Hacker News: n4pw01f

New comment by n4pw01f in "Fable 5 – Median thinking declined in August"

n4pw01f — Mon, 21 Sep 2026 19:27:13 +0000

The model improvements value are at the plateau of utility right now, peeling out small gains which is pretty “meh” in terms of business value

at this point frontier companies are just selling upgraded harnesses and tool calls with the rest of us

New comment by n4pw01f in "Ask HN: Are others seeing Google's reCAPTCHA rejecting Firefox users?"

n4pw01f — Tue, 08 Sep 2026 14:40:20 +0000

One interesting thing I found recently was after enforcing geo-fencing, recaptcha intermittently started failing. They might be using global edge servers or something

New comment by n4pw01f in "Small Models Have Arrived"

n4pw01f — Fri, 28 Aug 2026 17:56:39 +0000

I’m getting surprisingly good results on GEMMA4 2 bit, running on a Nvidia nano and raspberry pi

New comment by n4pw01f in "The Twelve-Factor App"

n4pw01f — Fri, 28 Aug 2026 17:54:56 +0000

Used to follow this to a T. Love 12factor, evangelized it at a lot of companies too

New comment by n4pw01f in "I were 17, I'd learn how to build LLMs from scratch"

n4pw01f — Tue, 25 Aug 2026 18:09:51 +0000

Hot take - but I’d learn to build CNNs from scratch. We are only just now scratching the surface of convolutional neural networks capabilities

New comment by n4pw01f in "Ask HN: Alternatives to GitHub"

n4pw01f — Mon, 17 Aug 2026 14:39:47 +0000

Self hosted GitLab has been good to me forever and has scaled and has a controllable attack surface as long as you keep on top of it

Newer app is moving to Google Cloud Secure Source Manager (because we are on Google Cloud and using backbone auth so it made more sense and less involved to manage)

New comment by n4pw01f in "Anthropic shares details about how Claude's new watermarks will work"

n4pw01f — Sat, 15 Aug 2026 23:01:30 +0000

If you look at how this works under the hood, “when two words that don’t necessarily matter to the context, it will pick one word over the other and a pattern emerges”

And that pattern will be reverse engineered in weeks by a startup

And a downstream agent produced by said startup will be built to roll those dice again and defeat the watermarking

And a the LLM vendors will combat this

And a cottage industry shall be born anew

New comment by n4pw01f in "Let's make the worst Htmx"

n4pw01f — Sat, 01 Aug 2026 02:35:03 +0000

Have a pretty large application running HTMX + WebComponents + Hono + Cloud Functions to serve up frontends, happy with it for about 2 years now

People throw salt at my stack but it’s fast, and straightforward to manage attack surface

New comment by n4pw01f in "Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac"

n4pw01f — Wed, 29 Jul 2026 22:33:21 +0000

Are you running bare metal or docker? I had to go down to 2 bit on Gemma4 E2B model to run on 8gb on a Jetson

Quality and idempotency is great but it’s still not exactly fast… fast enough and works offline

Is this something that you can get running on Debian?

New comment by n4pw01f in "Removing React.js from the codebase and adapting Htmx for UI interactivity (2023)"

n4pw01f — Mon, 27 Jul 2026 14:39:58 +0000

Replace React / Vue with HTMX 2 years ago and still going strong.

Hono + WebComponents + HTMX + serverless is the backend for my apps now.

New comment by n4pw01f in "Files over tools: how we built our agent with a virtual filesystem and bash"

n4pw01f — Thu, 09 Jul 2026 17:33:12 +0000

We ended up doing the same, own harness with a world view (schema.org) and map reduce rather than a RAG. Happy with the results and context hydration speed

New comment by n4pw01f in "Gemini 3.1 Pro"

n4pw01f — Thu, 19 Feb 2026 22:50:01 +0000

I created a nice harness and visual workflow builder for my Gemini agent chains, works very well. I did this so it would create code the way I do, that is very editable.

In contrast, the vs code plugin was pretty bad, and did crazy things like mix languages

New comment by n4pw01f in "Eight more months of agents"

n4pw01f — Tue, 10 Feb 2026 17:55:03 +0000

I am seeing shit tons of chatbots for everything under the sun being onboarded at corporate

New comment by n4pw01f in "France dumps Zoom and Teams as Europe seeks digital autonomy from the US"

n4pw01f — Tue, 03 Feb 2026 20:25:26 +0000

Why not Jitsi - genuinely curious

New comment by n4pw01f in "Please just try HTMX"

n4pw01f — Thu, 18 Dec 2025 18:27:01 +0000

I have used HTMX extensively with AI agents. It is fantastic for dynamic views.

Agent one: handles the request and does tool calls

Agent two: reads the result and decides on quality vs a re-drive if it’s low quality

Agent three: decides how to present the information to the user, creates a collection of HTMX elements

HTMX hx-get is reliably, and beautifully rendering the result of the Agentic Workflow without any react, etc.

Very happy and passing quality gates. I love not having security alerts every week to patch because of some buried react dependency library

New comment by n4pw01f in "The Bitter Lesson of LLM Extensions"

n4pw01f — Wed, 26 Nov 2025 23:21:30 +0000

I guess we just call them turn servers but technically it’s a “Stateful Dialogue Manager”

New comment by n4pw01f in "The Bitter Lesson of LLM Extensions"

n4pw01f — Wed, 26 Nov 2025 17:19:52 +0000

This process can be handled by a “turn server”

Was a pain to set up, but you can score the context completion and then if the score is under 98% or something, “ask” clarifying questions of the requesting agent or person or system