You’re right, but on the other hand once you have a basic understanding security, architecture, etc you can prompt around these issues. You need a couple of years of experience but that’s far less then the 10-15 years of experience you needed in the past.
If you spend a couple of years with an LLM really watching and understanding what it’s doing and learning from mistakes, then you can get up the ladder very quickly.
I find that security, architecture, etc is exactly the kind of skill that takes 10-15 years to hone. Every boot camp, training provider, educational foundation, etc has an incentive to find a shortcut and we're yet to see one.
A "basic" understanding in critical domains is extremely dangerous and an LLM will often give you a false sense of security that things are going fine while overlooking potential massive security issues.
Somewhere on an HN thread I saw someone claiming that they "solved" security problems in their vibe-coded app by adding a "security expert" agent to their workflow.
All I could think was, "good luck" and I certainly hope their app never processes anything important...
Found a problem? Slap another agent on top to fix it. It’s hilarious to see how the pendulum’s swung away from “thinking from first principles as a buzzword”. Just engineer, dammit…
But if you are not saving "privileged" information who cares? I mean think of all the WordPress sites out there. Surely vibecoding is not SO much worse than some plugin monstrosity.... At the end of the day if you are not saving user info, or special sauce for your company, it's no issue. And I bet a huge portion of apps fall into this category...
> If you spend a couple of years with an LLM really watching and understanding what it’s doing and learning from mistakes, then you can get up the ladder very quickly.
I don't feel like most providers keep a model for more than 2 years. GPT-4o got deprecated in 1.5 years. Are we expecting coding models to stay stable for longer time horizons?
My wife is a doctor and there is a general trend at the moment of everyone thinking their intelligence in one area (say programming) carries over into other areas such as medicine, particularly with new tools such as ChatGPT.
Imagine if as a dev someone came to you and told you everything that is wrong with your tech stack because they copy pasted some console errors into ChatGPT. There's a reason doctors need to spend almost a decade in training to parse this kind of info. If you do the above then please do it with respect for their profession.
> My wife is a doctor and there is a general trend at the moment of everyone thinking their intelligence in one area (say programming) carries over into other areas such as medicine, particularly with new tools such as ChatGPT.
My wife is a lawyer and sees the same thing at her job. People "writing" briefs or doing legal "research" with GPT and then insisting that their document must be right because the magic AI box produced it.
I'm reminded of an effect called Gell-Mann Amnesia.
When reading news stories on topics you know well, you notice inaccuracies or poor reporting - but then immediately forget that lesson when reading the next article on a topic you are not familiar with.
“A little knowledge is a dangerous thing” is not new, it’s a quote/observation that goes back hundreds of years.
> Imagine if as a dev someone came to you and told you everything that is wrong with your tech stack because they copy pasted some console errors into ChatGPT.
You mean the PHB? They don’t need ChatGPT for that, they can cite Gartner.
Agree, except I disagree that there is not much you can do.
You write "there is not much we can do in a police state against our current circumstances" and then you state "Our elected leaders on the opposition side are weak and spineless".
I would argue it's not just elected leaders that are being weak at the moment. Civil society too.
It's like saying sanctions will make N. Koreans or Russians rebel against their governments, and then wondering why none of them has done so, "are they cowards?". As if rebelling is so simple and not a life-changing thing...
There is a small window of opportunity to make this right. That window will be gone soon and then we would be in the N. Korean situation. Rebellion must be done early and enthusiastically. Each passing month makes it more and more difficult, in part due to boiling frog situation.
You don't live in North Korea, not even anywhere close. If you don't want to live in a state like North Korea, you need to use the democratic means you still have to make your voice heard. I am tired of this lazy defeatism
Luckily since USA is close to N. Korea your statement holds true. Glad to be not American.
Curiously enough if you do a survey of who of Kim Jong-Un and Donald Trump would be more likely to throw a world-threatening tantrum.. I don't think Kim Jong-Un is going to win that survey.
What a waste of resources to have to defend against one of your closest allies. This is a country that went to war on behalf of the US in Afghanistan (and lost 44 souls doing so). Disrespectful and shameful.
Wow that seems really strange to me to bring up that body count as some sort of guilt trip mechanism in your criticism. But if we are going to play that game, how about we also list how many Danish and US soldiers died in Europe during WW2.
higher social benefits, they think they will be receiving them forever.
However Greenlanders live in one part of Greenland and USA wants the other part so there is a simple solution.
Edit: You were complaining about 'environmental' HN users, but now you've edited your comment. I guess you read the article and were convinced, that's great :)
And we represent 0.1% of the population at best. Not really sustainable.
We are destroying the planet and we will come to regret this on our death beds. If anyone doubts that, go for a walk in nature and appreciate how incredible our ecosystems are, and how lucky we are to have that biodiversity, not AI agents.
Edit: I see you edited your comment from 'I have gotten gotten tremendous value from AI agents' to 'The US has gotten tremendous value from AI agents'. But the general point still applies.
If you spend a couple of years with an LLM really watching and understanding what it’s doing and learning from mistakes, then you can get up the ladder very quickly.
reply