Hacker News: TheGoddessInari

New comment by TheGoddessInari in "OpenCode – Open source AI coding agent"

TheGoddessInari — Sun, 22 Mar 2026 04:10:27 +0000

It's simple enough to make a plugin to override the system prompts & make it flexible per agent.

Have to watch out for other plugins trying to do the same, though.

New comment by TheGoddessInari in "OpenCode – Open source AI coding agent"

TheGoddessInari — Sun, 22 Mar 2026 02:26:00 +0000

Note as of yesterday, they retired the lite coding plan you're talking about. New buy-in is $50/month for the pro plan unless you were already on the lite plan.

New comment by TheGoddessInari in "Sci-Fi Short Film “There Is No Antimemetics Division” [video]"

TheGoddessInari — Tue, 17 Mar 2026 18:58:22 +0000

I feel like I have to mention "The Sky So Big and Black" by John Barnes. IMO, rather underrated. Hadn't really read any good Mars-based science fiction before.

New comment by TheGoddessInari in "Attyx – tiny and fast GPU-accelerated terminal emulator written in Zig"

TheGoddessInari — Wed, 25 Feb 2026 20:30:13 +0000

Aside from the AI bits, "interesting" choice to use metal on MacOS, opengl on Linux, and skip Windows entirely.

New comment by TheGoddessInari in "Show HN: Ghidra MCP Server – 110 tools for AI-assisted reverse engineering"

TheGoddessInari — Wed, 04 Feb 2026 20:41:22 +0000

Haven't dived deep into it yet, but dabbled in similar areas last year (trying to get various bits to reliably "run" in-context).

My immediate thought was to want to apply it to the problem I've been having lately: could it be adapted to soothe the nightmare of bloated llm code environments where the model functionally forgets how to code/follow project guidelines & just wants to complete everything with insecure tutorial style pattern matching?

New comment by TheGoddessInari in "Experts explore new mushroom which causes fairytale-like hallucinations"

TheGoddessInari — Sat, 27 Dec 2025 10:20:33 +0000

THC comes in a plant in the THCa form. CBD comes in CBDa form.

Both are not bioactive by default in their natural form.

New comment by TheGoddessInari in "The "confident idiot" problem: Why AI needs hard rules, not vibe checks"

TheGoddessInari — Mon, 08 Dec 2025 16:32:31 +0000

Like many chat-style interfaces, it's typically shift-enter to insert a newline.

New comment by TheGoddessInari in "Android and iPhone users can now share files, starting with the Pixel 10"

TheGoddessInari — Thu, 20 Nov 2025 19:03:26 +0000

There's a difference between "can't see 'special' folders" & "can't access anything but the app-specific storage". iOS loves the latter, while Android lets you organize files mostly normally even if doing highly stupid/discouraging things for power users & some app developers making questionable non-default choices.

New comment by TheGoddessInari in "I was right about dishwasher pods and now I can prove it [video]"

TheGoddessInari — Sun, 09 Nov 2025 21:38:34 +0000

Reductive and inaccurate.

New comment by TheGoddessInari in "Deepagent: A powerful desktop AI assistant"

TheGoddessInari — Sat, 25 Oct 2025 04:30:57 +0000

I've seen this on occasion before, but the offering seems vague and confusing to me.

But asking to see if clarification is available:

* No API access at all. Is that correct?

* Usage limits aren't at all clearly defined, but their presence is suggested. Message per day/month, tokens per whatever limits? * Content policy restrictions? They mention major models/providers. * An actual list of models available? GPT, etc, are cool if that's all you need, but what about major/popular open source models? * Encrypted/protected user content is mentioned, but do you allow verification by users that this is the case for compliance reasons? (This makes me think of providers that let you verify the nature of the secure computation yourself.)

This looks neat in theory, but there's nothing that goes into the exact technical nature of the offering. You may consider these suggestions for what might assist discerning technical users to have enough information about the service vs competitors that disclose all relevant information about the service up-front.

New comment by TheGoddessInari in "Attenborough’s long-beaked echidna rediscovered in Indonesia"

TheGoddessInari — Sat, 11 Nov 2023 00:47:38 +0000

Because the aliens are already here, just like the echidna...

New comment by TheGoddessInari in "-Werror Is not your friend (2017)"

TheGoddessInari — Sun, 01 Oct 2023 05:23:25 +0000

As an anecdote, there may be one or two packages in openwrt that won't build by default because of a strange interaction between certain glibc headers and the behavior of _FORTIFY_SOURCE on some embedded platforms, but only on some versions of gcc.

Werror tends to be placed eagerly pass the buck along to anyone building it, not just CI or developers. I used to feel that Werror was a good thing, but nowadays anything with CI on merge requests will tell me about any warnings, and someone wanting to build the software shouldn't get penalized for having a different build environment: there's a reason they aren't thrown as errors to begin with. Does this make sense?

New comment by TheGoddessInari in "A customer stuck due to a hurricane who needed SSH"

TheGoddessInari — Fri, 22 Sep 2023 08:07:08 +0000

IPv6 migration.

New comment by TheGoddessInari in "China's ancient water pipe networks show no evidence of a centralized authority"

TheGoddessInari — Fri, 08 Sep 2023 11:46:32 +0000

> Every human has their own hierarchies. Hierarchies of need, of goals and of peers (this is basically each individual's social hierarchy). But when these people form large groups they are somehow able to blank the slate and not make it hierarchical?

I'm probably being silly in doing so, but just pointing out that neurodiversity is a thing, and I don't know if you've noticed, but rarely do people simply do what they're told.

New comment by TheGoddessInari in "Radiation-hardened Quine (2014)"

TheGoddessInari — Fri, 02 Jun 2023 08:40:33 +0000

(2014)

New comment by TheGoddessInari in "Microsoft rewrites Windows font parsing in Rust"

TheGoddessInari — Wed, 26 Oct 2022 19:46:38 +0000

For Linux users,

New comment by TheGoddessInari in "The optimal amount of fraud is non-zero"

TheGoddessInari — Sat, 03 Sep 2022 19:34:00 +0000

I like this view: you take care of a lot of the conventional concern we while also some futuristic ones like Pre-Crime in Minority Report.

New comment by TheGoddessInari in "Embedding an EXE inside a .REG file with automatic execution"

TheGoddessInari — Fri, 29 Jul 2022 00:16:59 +0000

I have a USB mouse with 12 side buttons, and it "just works" because USB HID.

New comment by TheGoddessInari in "Gambling and Adult content DNS blocking using Mullvad VPN"

TheGoddessInari — Wed, 13 Jul 2022 15:45:13 +0000

The very thing you're linking to is because of running conflicting software on MacOS.

New comment by TheGoddessInari in "It's not your imagination – iPhone users are worse drivers"

TheGoddessInari — Sat, 07 May 2022 22:16:05 +0000

Android Authority is actually really calm compared to the source it's reporting on:

https://getjerry.com/studies/sorry-iphone-fans-android-users...