Hacker News: parasti

New comment by parasti in "Pokemon Emerald Ported to WebAssembly (100k FPS)"

parasti — Sat, 06 Jun 2026 13:38:06 +0000

You have to use "Add to home" menu item on Firefox for Android. But this web app doesn't seem to be a PWA.

New comment by parasti in "Ask HN: What was your "oh shit" moment with GenAI?"

parasti — Sat, 06 Jun 2026 08:23:48 +0000

I asked it how to configure haproxy, a tool that I had heard in passing about, and it gave me back exact working configuration syntax for my use case. Today that seems very mundane, but first time that happened, and I didn't have to google, read docs, or worst case sift through code, that blew my mind.

New comment by parasti in "Transformers are inherently succinct"

parasti — Fri, 05 Jun 2026 20:18:54 +0000

Paper went over my head but is this in any way related to my experience of Claude Opus 4.8 using increasingly terse language with very short, overloaded words? Lately I've been having trouble parsing the things it writes about my own code, it's using the kind of compressed language that you see typically in git commit message subject lines but relentless, always on.

New comment by parasti in "Artificial intelligence is not conscious – Ted Chiang"

parasti — Thu, 04 Jun 2026 08:58:04 +0000

> I think $my_species deserves to be debased in part because it's awfully egocentric and insist on being special in the universe.

This is a scary viewpoint to hold, for a human. If you despise humans, that's scary for me, as a human reader of Hacker News. Surprised to see this take unchallenged. I think we can recognize flaws in parts of humanity without wanting it "debased".

New comment by parasti in "Google's Antigravity bait and switch"

parasti — Thu, 21 May 2026 15:43:17 +0000

Google really outdid themselves this time. They killed not one but two tools (Gemini CLI and Antigravity) with one stone.

New comment by parasti in "Everything in C is undefined behavior"

parasti — Wed, 20 May 2026 10:23:21 +0000

Started in 2005. Never ever did anyone complain about UB in my years of writing C code and patching other people's C code. I knew it exists - as a spec quirk. (Admittedly, never wrote a compiler and never used anything except gcc and clang.)

New comment by parasti in "Gemini CLI will stop working from June 18, 2026"

parasti — Wed, 20 May 2026 09:13:08 +0000

Tried making an MCP server with Antigravity CLI. Antigravity CLI suffers from an identity crisis caused by a tool/ecosystem change: "I am unsure if I should be reading Gemini documentation, Gemini CLI documentation, Antigravity documentation or Antigravity CLI documentation". It couldn't really correctly answer how I should be registering the MCP server in its own system until I googled it.

New comment by parasti in "Everything in C is undefined behavior"

parasti — Wed, 20 May 2026 09:02:53 +0000

I have never in my 20 years of writing C heard so much about undefined behavior as I have in the past 6 months on Hacker News. It has never entered the conversation. You write the code. If it doesn't work, you debug it and apply a fix or a workaround. Why does the idea of undefined behavior in C get to the front page so consistently?

New comment by parasti in "Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep"

parasti — Mon, 18 May 2026 06:29:08 +0000

> These agentic AI's are already smart enough to figure out a highly optimized path to code exploration or search.

Hasn't been my experience. We used to use Augment Code at work which has a thing called Context Engine - basically an MCP that can answer natural language queries about pre-indexed code. Then we switched to Claude Code, which for some reason prefers to use sed to read from files using line ranges from its own memory (this despite having a range-capable read tool). I don't know, does that really mean that sed is the highly optimized path?

New comment by parasti in "Frontier AI has broken the open CTF format"

parasti — Sat, 16 May 2026 09:22:41 +0000

I can't help but draw parallels with video games. Aimbots in competitive multiplayer games is a well defined issue: it's considered cheating and frowned upon, players caught cheating are banned from the game. Tool-assisted speedruns (TAS) where a player attempts a world record at completion in a single-player game is another face of the same concept (computers help you win), but one that is socially accepted as long as runs are clearly labelled as TAS.

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

parasti — Thu, 07 May 2026 09:11:05 +0000

As a web developer, I feel like this take is wildly optimistic. My remaining qualifications that still provide some sort value are providing historical/business/architectural context to the agent and testing the agent's output. And that's only because 1) it's not all written down in Markdown and 2) the agent is massively nerfed by costs and Anthropic. The thing in the middle where I get a coffee and write code in a variety of languages, then pop open a debugger has been fully obsoleted.

New comment by parasti in "I have officially retired from Emacs"

parasti — Tue, 28 Apr 2026 20:25:09 +0000

My vim muscle memory has paid off more for me than my emacs muscle memory. Emacs was the better editor, though. Anything that doesn't have Vimscript is an automatic winner IMO.

New comment by parasti in "Stop Posting About Claude Getting Worse, You're Embarrassing Yourselves"

parasti — Sat, 25 Apr 2026 18:10:36 +0000

Wish this post was more technical, e.g., how is the author achieving the things they advise others to do. As is, the post can't seem to decide what it wants to be: is it a rant, is it a tech post, is it a brag, or something else? Are people embarrasing themselves when they're simultaneously affected by three bugs in Claude Code? How did the author avoid being affected by them?

New comment by parasti in "ChatGPT Images 2.0"

parasti — Wed, 22 Apr 2026 15:49:04 +0000

I get your point, but it's not even really that. It's that an AI generated photo evokes the same feelings in me that human-made photographs do and I have to catch that and turn that off consciously.

New comment by parasti in "ChatGPT Images 2.0"

parasti — Wed, 22 Apr 2026 06:04:43 +0000

A great technical achievement, for sure, but this is kind of the moment where it enters uncanny valley to me. The promo reel on the website makes it feel like humans doing incredible things (background music intentionally evokes that emotion), but it's a slideshow of computer generatated images attempting to replicate the amazing things that humans do. It's just crazy to look at those images and have to consciously remind myself - nobody made this, this photographed place and people do not exist, no human participated in this photo, no human traced the lines of this comic, no human designer laid out the text in this image. This is a really clever amalgamation machine of human-based inputs. Uncanny valley.

New comment by parasti in "Claude Opus 4.7"

parasti — Fri, 17 Apr 2026 06:03:15 +0000

Which open weights model?

New comment by parasti in "Don't feel like exercising? Maybe it's the wrong time of day for you"

parasti — Wed, 15 Apr 2026 06:50:31 +0000

That's funny. I've used that approach myself countless times to convince myself to do house chores. When your entire being seems to go "no, I really really really don't feel like doing it right now" and you just lay down the cold hard truth of "from your experience we know it's five minutes which is less time than most instances of doomscrolling". It's honestly perplexing why that part is the hardest part of the entire task.

New comment by parasti in "YouTube now world's largest media company, topping Disney"

parasti — Tue, 14 Apr 2026 19:54:28 +0000

The world's greatest library of knowledge is owned by a private US company. For some reason I am reminded of this more often than I care to admit.

New comment by parasti in "Turn your best AI prompts into one-click tools in Chrome"

parasti — Tue, 14 Apr 2026 19:47:46 +0000

These days announcements like this just make me want to put on my tinfoil hat - what's in it for Google, though? Why make it more convenient for people to submit webpages to you?

New comment by parasti in "A new spam policy for “back button hijacking”"

parasti — Tue, 14 Apr 2026 07:29:11 +0000

I understand this is vague on purpose but wish there was more detail. E.g., if I am running a game in a webgl canvas and "back button" has meaning within the game UI which I implement via history states, is my page now going to be demoted? This article doesn't answer that at all.