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.
> 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.
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?
>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.
Caring about the result, whether one "can tell the difference" or not.
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.
It doesn't look like self censoring at all - basically you want the default behavior of llms to gamble on the ethnicity of someone based on how they look.
Grok used a book as a reference.
It's not like ethnicity is a fact you infer from looking at someone.
Now ask Deepseek about what happened in Tiananmen Square and watch what censorship actually looks like.
It literally knows the facts, but then there's a layer that prevents it from stating the facts.
That's censorship.
It's not an opinion, it's not a choice when facing a gradient, it's just an historical known fact.
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.
With that volume of candidates, I'd be curious as to what they used for screening (AI prob?) and whether it was filtering out good candidates due to dumb filters.
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.
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.
reply