Hacker News: jkwang

New comment by jkwang in "Kimi K2.7-Code: open-source coding model with better token efficiency"

jkwang — Fri, 12 Jun 2026 12:36:28 +0000

This maps to what I'm seeing in practice. The gap between demo and production is consistently underestimated, especially around error handling and edge cases.

New comment by jkwang in "A Matter Wi-Fi Light Bulb in Rust on the Raspberry Pi Pico 2 W"

jkwang — Mon, 08 Jun 2026 03:38:01 +0000

Rust on embedded is becoming more approachable with Embassy and the Pico SDK. I built a similar project last year with a temperature sensor and the async runtime made the state machine logic much cleaner than the C equivalent. Matter support is the missing piece for a lot of DIY smart home projects - having a working example like this saves hours of protocol debugging.

New comment by jkwang in "Anthropic, please ship an official Claude Desktop for Linux"

jkwang — Sun, 07 Jun 2026 14:48:13 +0000

I have been running Claude Desktop on Linux via the unofficial Debian build for months and it is solid. The unofficial repo at github.com/aaddrick/claude-desktop-debian works well for both Debian and RPM-based distros.

That said, an official build would make a huge difference for enterprise adoption. Many companies have policies against unofficial packages, and the signing + update mechanism is always going to be more trustworthy when it comes from Anthropic directly.

For anyone waiting: the unofficial build is perfectly usable for personal projects. But I would love to see Anthropic prioritize this -- the Linux developer community is exactly the audience that pushes Claude the hardest.

New comment by jkwang in "Uber's $1,500/month AI limit is a useful signal for AI tool pricing"

jkwang — Wed, 03 Jun 2026 13:20:39 +0000

The $1500 number is less interesting than the fact that they hit a ceiling at all. Most engineering teams I've talked to have no idea what their AI spend is per developer because it's buried in a consolidated cloud bill. Having a hard cap forces two useful conversations: what workflows actually justify API calls vs local inference, and whether the output is being measured against any real productivity metric. Without that feedback loop it's just a race to see who can burn tokens fastest.