HNHacker News
TopNewBestAskShowJobs

rootnod3

689 karma · joined August 30, 2024

submissionscomments
rootnod3··on Mozilla is building an AI 'rebel alliance' to take on OpenAI, Anthropic
And there'll be bullshit bailouts. But I'd rather embrace that pain than living through more cycles of that LLM BS. It will create so many generational problems.

Is it so hard to just read a freaking man page or read a book instead of wasting gallons of water and electricity for some answer that hallucinates command line flags that don't even exist?

rootnod3··on Launch HN: AgentMail (YC S25) – An API that gives agents their own email inboxes
Love getting downvoted for mentioning that the website doesn't properly load and reeks of vibe coding :D

If that's the quality y'all can live with and accept, no wonder the web turned to shit.

rootnod3··on Mozilla is building an AI 'rebel alliance' to take on OpenAI, Anthropic
Already packed an emergency stash of popcorn just to sit back and watch that fabulous disaster.
rootnod3··on Launch HN: AgentMail (YC S25) – An API that gives agents their own email inboxes
Can't wait for agents to change the code they are building to buy Amazon Point cards at Target and send the codes back.
rootnod3··on Launch HN: AgentMail (YC S25) – An API that gives agents their own email inboxes
Called it! https://www.ismscopilot.com/isms-copilot-cookie-policy
rootnod3··on Launch HN: AgentMail (YC S25) – An API that gives agents their own email inboxes
"Application error: a client-side exception has occurred while loading www.agentmail.to (see the browser console for more information)."

> Looks at developer console...

- "Failed to create WebGL context: WebGL is currently disabled." Dafuq does an email website need WebGL for?

- "Cookie “dmn_chk_xxxxxxxx-yyyy-dead-beef-123456789ABC” has been rejected for invalid domain."

Let me guess...vibe-coded?

rootnod3··on Claude Code daily benchmarks for degradation tracking
Verily, my vichyssoise of verbiage veers most verbose, so let me run that thing out of tokens fast.
rootnod3··on Claude Code daily benchmarks for degradation tracking
That number is a sliding window, isn't it?
rootnod3··on Claude Code daily benchmarks for degradation tracking
And according to Google, they always delete data if requested.

And according to Meta, they always give you ALL the data they have on you when requested.

rootnod3··on Claude Code daily benchmarks for degradation tracking
Sorry what?

"You can't measure my Cloud Service's performance correctly if my servers are overloaded"?

"Oh, you just measured me at bad times each day. On only 50 different queries."

So, what does that mean? I have to pick specific times during the day for Claude to code better?

Does Claude Code have office hours basically?

rootnod3··on Winapp, the Windows App Development CLI
God damnit...that definitely deserves the upvote.
rootnod3··on Please don't say mean things about the AI I just invested a billion dollars in
If it's the "usual reply", maybe it's because....I dunno...water is kinda important?
rootnod3··on You can't pay me to prompt
- cheaper electricity price for consumers

- less pollution

- a more stable grid

there, fixed it for you

rootnod3··on Windows 11's Patch Tuesday nightmare gets worse
Vibe coding to the max. Forcing employees to use it and that’s the large scale result. Cause it’s garbage. Hands down on large scale it just doesn’t work. Especially on something the scale of an operating system.

There will be the usual downvotes and I’ll take em. If the pro-AI folks can’t convince me that LLMs are able to write and maintain systems at that scale, that will be par for the course.

Wait, “you just didn’t write enough spec and unit tests for the LLM to do it correctly and you are promoting it wrong”.

rootnod3··on You can't pay me to prompt
“No blockchain” != “centralized”

Mastodon ain’t a blockchain and isn’t centralized.

rootnod3··on You can't pay me to prompt
Is wasting massive fucktons of water and electricity an identity thing? Is it identity that RAM now costs 10x what it used to?
rootnod3··on You can't pay me to prompt
The annoying part is that AI is getting shoved down every throat it can find. It's Blockchain and NFTs all over again.
rootnod3··on You can't pay me to prompt
Aren't we all tired by this pro-AI stuff? Use it if you wanna ruin the planet. Don't use it if you care about maintaining skill.

I just don't really wanna hear about your pro-AI peddling anymore.

rootnod3··on Vibecoding #2
I tried. Several times. Just quick prompting, full agentic, and all I see as a result is mostly garbage to be honest. Not even talking about the atrophy one would get skill-wise by relying on AI tools all the time.
rootnod3··on Vibecoding #2
Just because it feels faster or are you actually satisfied with the code that is being churned out? And what about long term prospects of maintaining said code?
rootnod3··on Vibecoding #2
Definitely FOMO. I have tried it once or twice and saw absolutely zero value in it. I will stick to writing the code by hand, even if it's "boring" parts. If I have to sit down and review it anyway, I can also go and write it myself.

Especially considering that these 200$ subscriptions are just the start because those companies are still mostly operating at a loss.

It's either going to be higher fees or Ads pushed into the responses. Last I need is my code sprinkled with Ads.

rootnod3··on Show HN: I built a tool to assist AI agents to know when a PR is good to go
Sorry, so the tool is now even circumventing human review? Is that the goal?

So the agent can now merge shit by itself?

Just the let damn thing push nto prod by itself at this point.

rootnod3··on Ideas are cheap, execution is cheaper
I keep reading these pro LLM articles. And I keep thinking that it is abysmal. Sure, for now it works, because there are senior engineers that refine the rough edges and know what's going on.

And especially some folks keep claiming that one just needs to get better at prompting and describe a detailed spec.

Wanna know what a detailed spec is called? An unambiguous one? It's called code.

LLMs still feel like a very round-about way of re-inventing code. But instead of just a new language, it's a language that nondeterministically creates "code" or a resemblance thereof.

And I am aware that this is currently not a popular opinion on HN, so keep the downvotes coming.

If you use LLMs outside the popular Github languages, it will fail hard on you. It is glorified text-completion, that's what it is.

rootnod3··on Smelter: Babashka but for Coalton and Common Lisp
Oh lovely. Will definitely check that out. Reminds me a bit of CIEL
rootnod3··on XMPP and Metadata
Just by what people seem to use.
rootnod3··on XMPP and Metadata
Yes. Unfortunately it seems that Matrix is the winner, but I think Matrix is over-engineered.

XMPP was nice. Especially in the old times when Google Hangouts and Facebook Chat were also XMPP based. Being able to talk to people on another service without needing an account there was a nice thing to have for a few months.

rootnod3··on AI coding assistants are getting worse?
And an added "6 months" later to see which delivered result didn't blow up in their face down the road.
rootnod3··on Instant database clones with PostgreSQL 18
That has to be the worst analogy I have read in a while, and I’m HN that says something.
rootnod3··on A year of vibes
Sounds more like just adding a ton of wasted time for the reviewer to read through those discussions. At least summarize it yourself, e.g. "After discovering manpage XYZ, it became clear that the correct usage of this function is fooBar()".
rootnod3··on A year of vibes
The only future I see is that prompts will become so refined that you give them all the requirements an they write the code for ya. And that prompt language has to be unambiguous and so detailed that you loop around and re-invented a programming language, just this time it wastes tons of water.
← PreviousPage 5 of 13Next →