Hacker News: ianhxu

New comment by ianhxu in "Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers"

ianhxu — Thu, 18 Jun 2026 03:33:12 +0000

It is too difficult to strictly prevent the model from being used for any unsafe purpose. The same thing can be used for completely different purposes as long as it is described differently.

(Some) Unanswered Swift Group Questions

ianhxu — Fri, 12 Jun 2026 11:04:14 +0000

Article URL: https://www.massicotte.org/blog/wwdc26-unanswered-qa/

Comments URL: https://news.ycombinator.com/item?id=48502520

Points: 3

# Comments: 0

New comment by ianhxu in "Ask HN: What coding agents are you using?"

ianhxu — Thu, 11 Jun 2026 11:06:20 +0000

Claude Code and Codex are my daily drivers, and I often run them side by side on the same task to compare. For me Claude Code gets something working faster, but I burn the 5h quota on the $200 Max plan really fast. Codex I tend to trust a bit more on the careful diffs. The bigger change for me wasn't the tool though, it was writing a spec doc first (features/UX, technical, language-specific) before either agent touches code, then reviewing every diff. I still set up a lot of the harness by hand. How are people automating worktrees and parallel sessions?

Using Xcode 27's Agent Skills in Claude, Codex, and Cursor

ianhxu — Wed, 10 Jun 2026 12:00:25 +0000

Article URL: https://www.avanderlee.com/ai-development/using-xcode-27s-agent-skills-in-claude-codex-and-cursor/

Comments URL: https://news.ycombinator.com/item?id=48475011

Points: 1

# Comments: 0

Replacing Bash with Swift in an AI Harness

ianhxu — Thu, 04 Jun 2026 09:38:38 +0000

Article URL: https://alejandromp.com/development/blog/replacing-bash-with-swift-in-an-ai-harness/

Comments URL: https://news.ycombinator.com/item?id=48396260

Points: 3

# Comments: 0

Things I Think I Think about Coding Agents and IDEs

ianhxu — Thu, 28 May 2026 13:54:27 +0000

Article URL: https://blogs.newardassociates.com/blog/2026/titit-agents-as-ides.html

Comments URL: https://news.ycombinator.com/item?id=48308999

Points: 4

# Comments: 1

New comment by ianhxu in "Outsourcing plus local AI will soon become more economical vs. frontier labs"

ianhxu — Tue, 26 May 2026 14:29:30 +0000

>frontier models are more capable than the latest from DeepSeek. But is the capability difference enough to justify a 30x price difference?

The contradiction here is that without frontier models, there'd be no foundation for models like DeepSeek to reference and catch up to. Is there an economic model that captures this kind of dynamic?

New comment by ianhxu in "Leave Me Behind"

ianhxu — Mon, 25 May 2026 14:26:56 +0000

I don't have a quantitative way to argue this, but my intuition says that for humans to build something that matches human capability across every dimension would require a breakthrough at the physical level — and such a breakthrough may itself be bounded by the limits of humans as observers.

That said, this goal might itself be a non-goal. AI is going to be — or already is — more powerful than any individual human in many ways. But what my intuition points to is that humans will still have plenty of interesting work to do, like the author's example of handwriting code: it shifts from being scalable value creation into a form of craftsmanship.

New comment by ianhxu in "Leave Me Behind"

ianhxu — Mon, 25 May 2026 14:16:40 +0000

Like the artisans/craftsmen in many places (especially Japan), hand craft will always carry enduring meaning — machines ultimately can't replace everything humans shape with their hands. But historically at least, they can replace over 99.9% of it.

New comment by ianhxu in "Microsoft just banned its own engineers from using AI"

ianhxu — Mon, 25 May 2026 14:09:10 +0000

I don't see how tokenmaxx makes any sense without an effective way to measure impact per token (though measuring impact is inherently hard). I can easily burn through the entire 5-hour quota of the 200 Claude Max plan within the first 10 minutes.

I'm curious if companies can use Claude Code subscriptions the way individuals do. At the very least, this 200/month is one of the highest ROI investments I make. Compared to the at least 10k/month cost of an engineer at these companies, it's really a tiny expense.

New comment by ianhxu in "Search engines alternatives now that Google isn't Google anymore"

ianhxu — Mon, 25 May 2026 13:55:20 +0000

Not sure how Brave is. I'm using its API on OpenClaw, and so far my experience with OpenClaw has been satisfactory — though search is only one part of the overall quality.

I'd guess due to compute constraints, AI overview will struggle to reach truly great quality. That said, for now I find adding this section at the top still useful to me. The broader decline in Google's search quality is the bigger drag on me.

New comment by ianhxu in "The US is winning the AI race where it matters most: commercialization"

ianhxu — Thu, 14 May 2026 14:41:55 +0000

In a rapidly evolving field, the business environment in the United States may indeed have an advantage.

New comment by ianhxu in "A History of IDEs at Google"

ianhxu — Thu, 14 May 2026 14:35:44 +0000

Been using Cider for two years now. Early on I struggled, trying to use IntelliJ, and even tried the thin client version — but both are basically in maintenance mode. Cider is the de facto standard. It really is the best IDE in terms of integration with internal tools, but it also inherits Google internal tooling’s general disregard for UX quality and aesthetics.

New comment by ianhxu in "Show HN: Agent-skills-eval – Test whether Agent Skills improve outputs"

ianhxu — Thu, 07 May 2026 12:09:07 +0000

exactly

New comment by ianhxu in "Write some software, give it away for free"

ianhxu — Thu, 07 May 2026 10:14:04 +0000

"A rich aristocrat in a society of slave holders" is certainly one type, but there are many other types that still meet mainstream standards today, such as heirs to fortunes, tenured university professors, etc.

New comment by ianhxu in "Show HN: Agent-skills-eval – Test whether Agent Skills improve outputs"

ianhxu — Thu, 07 May 2026 10:08:40 +0000

How do you iterate on the judge prompt? Is there an auto rater?

New comment by ianhxu in "Vibe coding and agentic engineering are getting closer than I'd like"

ianhxu — Thu, 07 May 2026 10:01:34 +0000

In my own experience, good engineering practices are still not easy to achieve. As a software engineer with three years of experience, I've been doing solo dev for the past few months. Currently, there is still a lot of the harness to set up manually.

New comment by ianhxu in "The Boring Internet"

ianhxu — Wed, 06 May 2026 10:15:03 +0000

The ux is really bad. But the commenting, versioning, syncing functions for collaboration or cross-platform use are of high-quality. And that's actually Google vs. Apple.

New comment by ianhxu in "The Boring Internet"

ianhxu — Wed, 06 May 2026 09:50:25 +0000

Not sure. Without commercialization and ads, there might not be the free high-quality web apps from Google. Things have two sides. But the complexity of the internet should have far surpassed the level that even large corps could influence, and therefore, the key might be culture instead of tech.

New comment by ianhxu in "Write some software, give it away for free"

ianhxu — Wed, 06 May 2026 09:36:59 +0000

This is a wonderful ideal. Like some ancient scientists and philosophers, they don't have many worries about money and can pursue pure passion. This also seems like a key source of social progress -- diverse purposes and paths of exploration.