dan_q

> Speaking of that "obviously impressive" line, I'm getting really tired of something like that line seemingly needing to be included by anyone doing any criticism of agentic systems. The most common form of it is "these models are obviously useful" midway through a bunch of arguments about environment, data provenance, skill atrophy, or even correctness issues.

> Why does everyone feel the need to equivocate?

Blame the mods here for that. This is the first week since 2023 I haven't had a HackerNews account banned for directly critiquing LLM code generators.

> I want to tell these people to just cut it out. It's demeaning to their own position.

I couldn't agree more. It's a rhetorical disaster.

> I don’t believe for a second that they lack the engineering talent.

Let's agree to disagree. Remember flicker-gate? https://news.ycombinator.com/item?id=48403908

> But the event itself only seems possible because they failed to properly monitor and isolate the environment in the first place.

OpenAI is clearly run by dummies and subpar engineering talent.

> The model is obviously impressive

Speak for yourself.

> Isn't this a show of security negligence rather than of exceptional agent capabilities?

Seems to me you could say this about all enterprise adoption of "AI" since 2023.

I'd like to see Dario Amodei and Sam Altman fight to the death in a gladiator battle. Both of these guys are so fucked up that I think regardless of who won, the winner would rape the other's dead corpse in the ring.

> This feels straight out of sci-fi.

Most AI marketing is straight up science fiction.

> did anyone else have the feeling that, for all their messaging around “we are so afraid that our models will be used for hacking”, they sure as hell are trying their best to make their models razor focused on precisely that purpose?

That's the point. It's like a pool hall with "NO GAMBLING" signs posted on the walls.

The message is that the hall is intended for gambling, but that the hall's patrons may be held liable if the situation becomes inconvenient for the proprietor.

In this case, the product is intended for hacking, but of course the user may be held liable if the situation becomes inconvenient for the model's proprietor.

At my job in 2023, after the staff engineers quit, new-hire engineers backed by new-hire managers pushed through a series of 5,000-10,000 line GPT 3.5 PRs affecting ludicrously convoluted, critical Makefiles designed and maintained by engineers who had left the company because of AI initiatives.

Even when AI couldn't write a line of code to save its life, I watched this company push out its strongest engineering talent to replace a series of well-constructed codebases with subhuman AI slop. They hired a wrecking crew of managers and engineers who were incentivized to ram the AI slop through as quickly as possible.

> On what planet do people start paying for things without keeping an eye on the costs and no-one notices until you have spent a crazy amount? I don't understand. You are either paying a fixed amount which you are happy about in-advance or you are PAYG in which case you would ballpark how much it costs.

The AI rollout has in large part been about giving management an opportunity to say "fuck you" to engineering.

Engineering payroll needed to be slashed and the C-Suite was happy to let their managers get some lashes in on the uppity workers.

The point of AI is:

1. It's bad engineering and everyone knows it.

2. Management is pushing it through anyway.

3. Deal with it, asshole.

The ROI is besides the point. It's about breaking the spirit of engineering labor with irrational decisions made outside of their control.

Edit: It is just as much about affirming the exalted status of management in comparison to labor. It's a bitter reinscription of the status hierarchy in tech; Management is good and labor is bad; Management is considerate and labor is ignorant; Management is strong and labor is weak; Management is superior and labor is inferior.

> The industry has always been stupid and selfish and short-sighted but now the ICs at the bottom of the pyramid are themselves being commoditized like all the workers they "disrupted".

Are you allowed to use the word "union" on this website?

The "us" vs "them" thought pattern is the essence of "Western" (read: white, European, colonialist) culture, dating back to Plato's Republic.

Marimba Ani's seminal work Yurugu is a sociological study of this culture from a non-western perspective. I can't recommend it strongly enough if you want to understand the nexus of social/psychological/epistemic factors that sustain the "us" vs "them" thought pattern and its corresponding cultural manifestations.

https://archive.org/details/yuruguafricancen0000anim/page/n3...

> There are still many places where engineers or knowledge workers are respected and left to lead (or not) AI adoption.

Please start naming names

This site aggressively suppresses any criticism of LLMs, especially LLM generated/"assisted" code.

2022/2023 is when the AI wrecking crews came in in full force

> when i brought this up with my manager they just said "WORK HARDER, SLAVE"

> most importantly developers saying "we no longer know how this code works but it's massively bloated and unreadable and we can't tell you with a straight face that we can maintain it or fix it if it breaks."

To anyone reading this: If you couldn't see this coming three years ago, you don't deserve your job.

> We have seen a flood of vibe-PRs from engineering adjacent teams that suddenly think they can code shipping prototypes into production that do not work do not scale and cannot be maintained.

What a nightmare. Never forget that AI is for idiots.

Quit cold turkey and you can drive down AI coding spend 100%.

You're mad.

> which in your case is?

oh, they're mad.

I don't believe that you're asking in good faith based on the rest of your comment.

I don't think you should take "AI-first developers" seriously as a category.

The people you refer to are delusional idiots and should be treated as such.

> For that, you'd want the list of requirements and hardware documentation to be written in a precise, formal language. That's no different than writing them in a programming language (though a declarative one, instead of the more common imperative ones).

From my perspective, this is a damning conclusion to the argument.

That being said, I can hear him asking Claude to generate a rebuttal as we speak.

> It's true they don't HATE people

Maybe so, but perhaps the most successful part of the AI marketing pitch has been exploiting management's hatred of labor (and vice versa).

A significant motivator for a lot of the nonsensical AI layoffs and initiatives over the last three years has been that it's a great opportunity for management to get ill on their slaves.

Tech labor got a little too big for their britches during the hiring spree of 2021, and AI was a great opportunity to take them down a peg, even if it offered little in the way of ROI.

> Wow, fantastic, you can build all your software in house, zero dependencies. Wait, your users can do the same? And they don’t need to pay you anymore for any of your cool services because they just asked their agents to recreate your infra from scratch?

The cherry on top is that OpenAI and Anthropic brainwashed your coworkers and your company's C-suite into uploading the entirety of the "proprietary" codebase onto their servers thousands of times per day over the last three years.

Let me guess: AGI is 2-6 weeks away, software development is solved, and anyone who disagrees with your enlightened perspective is a backwards-looking luddite.

This constitutes an admission on the part of one of the largest AI investors that AI generated/"assisted" code is inadequate (in part) because it is produced in flagrant violation of license rights.

AI is for people who are proud of their obduracy.

The Oracle AI ban marks the end of the Kayfabe era.

Even the biggest institutional AI investors have to ban their contributors from spamming them with AI generated slop.

I know you've heard this one before: "Never get high on your own supply."

Why not just write the code yourself? You sound like an addict hiding their use from their friends and family.