HNHacker News
TopNewBestAskShowJobs

rootnod3

689 karma · joined August 30, 2024

submissionscomments
rootnod3··on Addressing Antigravity Bans and Reinstating Access
Here’s an idea: run your digital life away from a corporate shitbucket like Google. Don’t run your email there. Plenty of good other options.
rootnod3··on Show HN: X86CSS – An x86 CPU emulator written in CSS
> What you're seeing above is a C program that was compiled using GCC into native 8086 machine code being executed fully within CSS.

They did write 8086 in the text, but x86 in the title.

rootnod3··on Child's Play: Tech's new generation and the end of thinking
This hits especially hard for projects like OlenBSD and FreeBSD. The unsung heroes.

Linux gets some fame and recognition, meanwhile OpenBSD and FreeBSD are the ones they power routers, CDNs and so many other cool shit while also being legit good systems that even deserve attention for the desktop.

rootnod3··on Ask HN: Why is my Claude experience so bad? What am I doing wrong?
> Finally: Cloudlflare builds OAuth with Claude and publishes all the prompts: https://hw.leftium.com/#/item/44159166

Lord help us

rootnod3··on Why I don't think AGI is imminent
Anyone who thought it’s near clearly hasn’t opened a book in a long time.
rootnod3··on OpenAI should build Slack
Sorry, but why should they? What makes OpenAI better at making Slack than....Slack? Sure, Slack can be improved, but why the fuck should that be done by OpenAI? Shouldn't OpenAI concentrate on...I don't know....AI?! And first try to break even on that promise and actually generate revenue on that shitty promise?
rootnod3··on Common Lisp Screenshots: today's CL applications in action
Ah, so I need to pay 100s of $ and use the "frontier" model, which is always a moving BS excuse. Last month Opus 4.5 was the frontier, gotta use it, now it's 4.6, and none of them so far have produced anything consistently good.

It is NOT reasoning about code. It's a glorified autocomplete that wastes energy. Associating "reasoning" to it is an antropomorphizateion.

And calling hallucinations "lateral thinking" is a fucking stretch.

"Let's use tool `foo` with flag `-b`" even if the man page doesn't even mention said flag.

Sure, they might be able to create numerous iterations of containers, testing them, burning resources....but that is literally a thousand monkeys smashing their heads on typewriters to crank out 4chan posts.

rootnod3··on Common Lisp Screenshots: today's CL applications in action
Highly recommend https://github.com/fosskers/vend
rootnod3··on Common Lisp Screenshots: today's CL applications in action
Until there is a bug and say due to DNS issues your LLM is. It reachable because everything is down
rootnod3··on Common Lisp Screenshots: today's CL applications in action
Really? Feels like most Of HN lately is just “get on the AI hype train or get downvoted”
rootnod3··on Common Lisp Screenshots: today's CL applications in action
Can your LLM do that to a running system? Or will it have to restart the whole program to run the next iteration? Imagine you build something with long load-times.

Also, your Lisp will always behave exactly as you intended and hallucinate its way to weird destinations.

rootnod3··on GitHub Agentic Workflows
Ah yes, lovely. That's what I want in my CI/CD...hallucinations that then churn through I don't know how many tokens trying to "fix it".
rootnod3··on My AI Adoption Journey
Exactly the point. AI is absolutely BS that just gets peddled by shills. It does not work. It might work for some JS bullcrao. But take existing code and ask it to add capsicum next to an ifdef of pledge. Watch the mayhem unfold.
rootnod3··on My AI Adoption Journey
How is it more expressive? What is more expressive than Turing completeness?
rootnod3··on My AI Adoption Journey
Just create a very specific and very detailed prompt that is so specific that it starts including instructions and you came up with the most expensive programming language.
rootnod3··on My AI Adoption Journey
Absolutely this. I am tired of that trope.

Or the argument that "well, at some point we can come up with a prompt language that does exactly what you want and you just give it a detailed spec." A detailed spec is called code. It's the most round-about way to make a programming language that even then is still not deterministic at best.

rootnod3··on [dead]
See, what’s missing is agentic posting. Let it write to itself a few times and simulate some reactions, then do the actual post.
rootnod3··on Coding Agent VMs on NixOS with Microvm.nix
And you see no problem in that at all? Just “throw a box around it and let the potentially malicious code run”?

Wait until they find a hole. Then good luck.

rootnod3··on My five stages of AI grief
Claude 4.5, all variants, Rust, C, Common Lisp and Haskell.
rootnod3··on Data centers in space makes no sense
And burn even more energy and fuel than DCs on the ground, great idea :D
rootnod3··on Data centers in space makes no sense
Forget heat. Replacing disks alone is a deal breaker on that one.
rootnod3··on Data centers in space makes no sense
“Musk is on to something here”? Really? Any high school student with a basic grasp of physics could explain that. But sure, the idiot billionaire nazi “is on to something”. That’s giving him too much credit.

Of course it doesn’t fucking make sense to put data centers into space. Even if heating were solved somehow magically, server disks are veeery prone to fail and need replacement. Shoot a rocket up every week to replace failed drives or absolutely burned through GPUs? Yeah, that doesn’t even remotely sound feasible.

rootnod3··on Coding Agent VMs on NixOS with Microvm.nix
That is quite an involved setup to get a costly autocomplete going.

Is that really where we are at? Just outsource convenience to a few big players that can afford the hardware? Just to save on typing and god forbid…thinking?

“Sorry boss, I can’t write code because cloudflare is down.”

rootnod3··on My five stages of AI grief
I must be using it wrong then or using the wrong languages. All I have seen it produce so far was mediocre at best and painfully wrong 2-3 prompts in.

Not even starting with how it just “fixes” a hug by introducing a wholly new one and then re-introducing the old one when pointing it out.

rootnod3··on Hypergrowth isn’t always easy
I think part of "grow naturally" assumed no investors. Just be self-sustaining with maybe some extra.
rootnod3··on Where I'm at with AI
for<TAB>….

Yeh, you are right. A snippet for they would have taken longer than booting an agent and let it hallucinate for—loop parameters that didn’t even exist.

rootnod3··on Where I'm at with AI
Almost. It’s worse though. It’s using snippets without using grey matter and shifting blame if needed.

A snippet for a for loop in your editor, yeah, go ahead. A “snippet for “make this spec into half assed code” is a wholly different story.

Overpaid bubble snippets at best.

rootnod3··on Where I'm at with AI
It’s already causing massive problems before we even got to models that even do anything actually useful.

Wait until other countries jump in the bandwagon and see energy prices jump.

Currently it is mostly the US and China.

And RAM and GPU prices are already through the roof with SSDs to follow.

That is for now with ONLY the US market mostly.

And those “net benefits” you talk about have very questionable data behind it.

It’s a net loss of you ask me.

rootnod3··on Where I'm at with AI
And most of those concerns being wildly dismissed by the AI shills, even here on HN.

Mention anything about the water and electricity wastage and embrace the downvotes.

rootnod3··on Launch HN: AgentMail (YC S25) – An API that gives agents their own email inboxes
I have a strong guess on how that website was coded....
← PreviousPage 4 of 13Next →