rotis

So the AIs end up being silly like in this video?

10 AIs Play Mafia

https://www.youtube.com/watch?v=JhBtg-lyKdo

I have problems reconciling this story with the Amazon one from few days ago. If we take both for truth doesn't that basically imply Amazon researchers got scared by the ‘Fix this code’ prompt first and then spooked the feds? Shouldn't we make fun of those researchers first? I don't know. I feel there lies a lie somewhere in the open.

Agentic engineering? Vibe coding? That is so yesterday. Chain-of-thought flow is where it is at now. You heard it here first folks. Early examples of such phenomena include Rube Goldberg machines

https://x.com/i/status/2053560589327180255

I sense a pattern emerging.

Are you suggesting intelligent design got us here?

Not really convinced by the first graph (and following too). According to it on a 10 year old project developers only manage to spend 10% of their available time adding features because rest is consumed by maintenance? By 10 year landmark I would expect most of software to be mature, with less new features needed and most known bugs fixed.

Got it. Vibe coding is all about the end result, damned be the way we got there. So I assume agentic engineering must be the opposite here? Don't care what we will cook. If I get a calculator while asking for integrator that is the true agentic engineering.

Caring about what? I could slap an application and say I vibe coded it or I could equally claim I agentically engineered it. No one could tell the difference(if there is any) without seeing the code. The only thing you could say I used an LLM. And that is what is happening. Most of the code that is "engineered" we don't get to see. So who know what is really going on there and what is the actual result?

my disturbing realization that vibe coding and agentic engineering have started to converge in my own work.

I firmly staked out my belief that “vibe coding” is a very different beast from responsible use of AI to write code, which I’ve since started to call agentic engineering

Disturbing? Really? I admit I don't do agentic and am going only by vibes, but for me agentic engineering is basically vibe coding in a automated loop with some ornamentals. They both stem from the same LLM root and positioning them as significantly different is weird and unconvincing to me. There may be a merit to this article (I gave up after few sentences), but I reject this specific premise.

https://chatgpt.com/share/69f0dc83-ec70-83eb-896b-b258de2c9f...

https://claude.ai/share/ac4d2041-4328-4511-904a-ff8b1cbfc0bb

Looks like self-censoring to me. Grok has no problems answering, so it is not a technical limitation:

https://grok.com/share/bGVnYWN5_341d6428-ea7d-4b84-ad4d-8df9...

I don't have a problem with AI assistance either, but this undermines the point the article is making. For me it is like a priest preaching gay sex is wrong and then being caught in bed with a male prostitute (snorting cocaine optional). Leaves bad taste in the mouth.

He writes 2,253 candidates and 2,069 were disqualified. 184 were qualified, so 1 in 12 was considered competent.

Asking ChatGPT about safety of someone traveling instead of asking that person is the nerdy thing to do. Somehow a hairstylist doesn't invoke image of a nerd in me. That is why I find this story implausible.

Agreed. Lead main source in nature is galena, which is relatively nontoxic. It rarely occurs in metallic form.

The fire started on 26th September and news about it reached HN only now. I think this is telling how disruptive for South Korea daily life this accident really was.

Reminds me of one of the stupidest hacks I discovered (In my mind). In one of my previous companies we had many similar Lotus Notes databases and one of them didn't allow to copy text from it. You could paste, I'm sure. You could select the text. But not copy. Turns out you could DRAG the selected text to other window. This copied the text over. So being able to highlight a text may mean you can indeed copy it ;)

I'm sceptical a layperson will understand or care what it means that their data will be used in training. If you are concerned about such things this heavily implies you don't want to share your data. Just don't agree to the terms and move on.

Exactly. This is a basic optimization technique and all the dinosaur era databases should have that. But if you build a new database product you have to implement these techniques from scratch. There is no way you shortcut that. Reminds me about CockroachDB and them building a query optimizer[1]. They started with rule based one and then switched to cost based. Feature that older databases already had.

[1] https://www.cockroachlabs.com/blog/building-cost-based-sql-o...

Everything else aside moving to R and Python to escape the USA hegemony means you are still dependend on Python Software Foundation and R Fundation. First is American. Second is based in Vienna, Austria yet still has big American presence among its members. So you end up still dependending on USA. Same with most free and open source. Even if its authors may appear to be European, they may turn out to be Americans (Linus Torvalds) or work for US company anyway (Guido van Rossum)

All that and who will pay for it? Politicians? They use taxpayers money. Companies? They will pass on the bill to the customers. So in the end same group will experience higher prices. I can't wait for all the poor becoming poorer.

Yes, this paper and many others will be forgotten as soon as they leave the front page. Afterwards noone refers to articles like these here. People just talk about anecdotes and personal experiences. Not that I think this is bad.

That's another issue I have with this article. It lists the risks, but does not provide any specific well documented examples. It (and many others privacy related) does not try to quantify them either. Driving a car, flying a plane pose risks too. Yet milions of people take the risk daily. Jumping from 10th floor is also risky and here somehow most peoply don't try it. People intuitively can evaluate the risks on their own and ultimately you cannot do that for them. If examples of negative consequences of their data being sold start appearing, they will stop using these apps by themselves. But I personaly think these risks are blown out of proportion.

The author defends mediocore code, yet wrote this piece:

https://fly.io/blog/vscode-ssh-wtf/

Where he dunks on how SSH access works in VSCode. I don't know. The code and architecture behind this feature may well be bananas, but gets the work done. Sounds like a clear case of mediocority. I wonder how does he reconcile those two articles together.

For me this is more of a clickbait. Both of the articles. With that in mind, if I am nuts for being sceptical of LLMs, I think it is fair to call the author a clickbaiter.

I dunno. Cultural exchange has positive connotations in my book.

To add to sibling comment. This sounds like a parameter sniffing. Read it up. It should help you understand the problem. It is a known issue with SQL Server. Or rather a tradeoff. You don't want to compile a new execution plan for every query. This would eat up CPU by itself.

Atmosphere of this exoplaned is rich in hydrogen. Also it has likely different atmospheric pressure than we have on Earth. Doubtful there is any life form as we know it. I suspect best we can expect there is something like a primordial soup: a mix of relatively simple organic compounds.

How can this article be written by LLM? Its date is November 2021. Not judging the article as a whole but the command you pointed out seems to be correct. Faster is the name of the pool.

This sounds very similar to Cuzz from Application Verifier for Windows:

https://learn.microsoft.com/en-us/windows-hardware/drivers/d...

Mirrors my experiences with z/OS. One thing I distinctly remember was when I tried to write JCL to move some datasets. Took me 2 days reading documentation and trying out things. Finally I just gave up. It is not fun when you have noone to help and Google isn't very helpful. If you think Unix tools have no consistency, try JCL and z/OS. Considering how alien JCL is and magic incantations I invoked with it, I'm convinced that there is Cthulhu in the mainframe machine.

Still, I'm quite proud I manage to write some JCL which saved us potentially days of manual work.

Other things I remember from that time was that passwords were only 8 characters long and case insensitive. My guess is z/OS is secure only by its obscurity. Though maybe this was just our installation. No idea until today.

Here are the marriage ages for US and the world for context:

https://en.wikipedia.org/wiki/Marriageable_age

https://en.wikipedia.org/wiki/Marriage_age_in_the_United_Sta...

The US doesn't seem to particularly stand out. I feel this article is manipulative and just tries to antagonize people. Manipulative because it says some marriages were for children aged 10, while the minimum age is usually 15/16. So how is this even possible? Those 10 year child cases should definitely be investigated, but I'm sceptical that's anything more of a small fraction of underage marriages and they are probably illegal to begin with. The antagonizing part is simple: It's all Republicans. Don't mention that California has technically no official age defined. This would break the narrative.