Hacker News: AnonyX387https://news.ycombinator.com/user?id=AnonyX387Hacker News RSShttps://hnrss.org/hnrss v2.1.1Tue, 07 Apr 2026 19:23:07 +0000<![CDATA[New comment by AnonyX387 in "Claude Code is being dumbed down?"]]>The UX where it completely breaks copy paste conventions on Linux? Other than that I agree it's gotten pretty good but this one thing drives me mad each time I use it.

]]>Wed, 11 Feb 2026 18:48:29 +0000https://news.ycombinator.com/item?id=46979051AnonyX387https://news.ycombinator.com/item?id=46979051https://news.ycombinator.com/item?id=46979051<![CDATA[New comment by AnonyX387 in "Instabridge has acquired Nova Launcher"]]>Haven't seen the app switching issues with Lawnchair for a long time, both on pixel 6 and pixel 9. So I think this might finally be resolved..

]]>Wed, 21 Jan 2026 14:38:01 +0000https://news.ycombinator.com/item?id=46706301AnonyX387https://news.ycombinator.com/item?id=46706301https://news.ycombinator.com/item?id=46706301<![CDATA[New comment by AnonyX387 in "Provide agents with automated feedback"]]>I've only used Claude's planning mode when I just started using Claude Code, so it may be me using it wrong at the time, but the superpowers are way more helpful for picking up on you wanting to build/modify something and helping you brainstorm interactively to a solid spec, suggesting multiple options when applicable. This results in a design and implementation doc and then it can coordinate subagents to implement the different features, followed by spec review and code review. Really impressed with it, I use it for anything non-trivial.

]]>Mon, 19 Jan 2026 08:30:17 +0000https://news.ycombinator.com/item?id=46676330AnonyX387https://news.ycombinator.com/item?id=46676330https://news.ycombinator.com/item?id=46676330<![CDATA[New comment by AnonyX387 in "Provide agents with automated feedback"]]>> Right now i spent a lot of “back pressure” on fitting the scope of the task into something that will fit in one context window (ie the useful computation, not the raw token count). I suspect we will see a large breakthrough when someone finally figures out a good system for having the llm do this.

I've found https://github.com/obra/superpowers very helpful for breaking the work up into logical chunks a subagent can handle.

]]>Mon, 19 Jan 2026 06:48:45 +0000https://news.ycombinator.com/item?id=46675726AnonyX387https://news.ycombinator.com/item?id=46675726https://news.ycombinator.com/item?id=46675726