> And to top it off, Claude (the supposed expert tool) didn't repeatedly output "Are you insane?

It did though acoording to the article and he ignored it.

The Ai can only work with what you tell it.

The difference is, an expert engineer would flat-out refuse to do these things and would keep pushing back. Claude may sometimes attempt _one time_ to warn someone, and then (after consent fatigue means they're just blindly clicking "yes"), it ploughs right ahead without further complaint.

Do you really want the Ai to not do the things you tell it?

It only knows what you tell it, if you tell it risky operations are OK, what do you expect?

That depends.

As per my root comment, if you ignore a lot of the marketing of AI and view it as just a tool, then I agree with your point about it doing what you tell it but I still want the tool to help me avoid making mistakes (and I’d like it to work quite hard at that - much harder, it seems, than it currently does). And probably to the extent that it refuses to run dangerous commands for me and tells me to copy/paste them and run them myself if I really want to take the risk.

If, however, we swallow the marketing hook, line and sinker: then yeah, I want the AI to behave like the experienced engineer it’s supposed to be.

An experienced engineer still gets decisions overridden all of the time and has to suck it up or get fired.

True.. though an experienced engineer would also risk getting fired for doing all the other stuff the OP did too. Especially if they made minimal attempts to highlight consequences/outcomes to management in advance..

I don't think your saying the same thing. Ai can help you get through the hard stuff effeciently and you'll learn. It acts as a guide, but you still do the work.

Offloading completely the hard work and just getting a summary isn't really learning.

What companies are hiring people to use rust?

Loads, I come across it frequently and I'm not actively looking for them.

This is what in praise of idleness is about.

Ops hasn't been in the crosshairs of Ai yet.

Imo it's only a matter of time as companies start to figure out how to use ai. Companies don't seem to have real plans yet and everyone is figuring out ai in general out.

Soon though I will think agents start popping up, things like first line response to pages, executing automation

We've had deterministic automation of tier one response for over a decade now. What value would indeterminacy add to that?

To deal with the problems where there is ambiguity in the problem and the approach to solving it. Not everything is a basic decision tree. Humans aren't deterministic either, the way we woukd approach a problem is probably different. Is one of us right or wrong? We're generally just focused on end results.

Maybe 2 years ago Ai was doing random stuff and we got all those funny screenshots of dumb gemini answers. The indeterminism leading to random stuff isn't really an issue any more.

The way it thinks keeps it on track.

Two weeks ago I asked a frontier model to list five mammals without "e" in their name and number four was "otter"

Is identifying mammals without the letter E part of your ops work flow?

Opus 4.6 didn't have an issue with this question though.

> Is identifying mammals without the letter E part of your ops work flow?

No, but it can show unreliability for adjacent tasks. Identifying a CIDR block in traffic logs is a normal part of an ops work flow. It means it's more likely to fail if you need to generate a complex Regex to filter PII from a terabyte of logs. If the model has a blind spot for specific characters because it tokenizes words instead of seeing individual characters, then it can miss a critical path of failure because the service name didn't fit its probabilistic training.

Maybe you need to boilerplate Terraform. If the model can't reliably (reliably, as in, 100% deterministic, does this without fail) parse constraints, it's not just a funny mistake it's a potential 5 figure billing error.

Ops can't run on "mostly accurate." That's just simply not good enough. We need deterministic precision.

For AI to be useful in this world to the extent others have claimed it is for software eng, we'll likely need more advanced world models, not just something that can predict the next most likely token.

Your terraform written by a person already doesn't have deterministic precision. Ai isn't messing these things up either.

If your Ai work flow is still dumping logs into a chat and saying search it for some pattern, then you should see what something like Claude code approaches problems. These agents aren't building scripts to solve problems. Which is your deterministic solution.

That still only just makes it a force multiplier for engineers, like any other tech, not a replacement as it's being hyped and sold as.

Claude resorting to writing code for everything, because that's all the model can do without too many hallucinations and context poisoning, is just a higher speed REPL. Great, that's useful.

But that's not what is being hyped and sold. What's being hyped and sold is "You don't need an Ops guy anymore, just talk to the computer." Well, what happens when the AI decides the "fix" is to just open up 0.0.0.0/0 to the world to make the errors go away? The non technical minimum wage person now just talking to the computer has no idea they just pwned the company.

If AI's answer is "Just write a script to solve the prompt" then you still need technical people, and it's vasly over hyped.

I'll be interested when you actually can just dump logs in a chat and analyze it without the model having to resort to writing code to solve the problem. That will be revolutionary. Imagine all the time I'd save by not having to make business reports, I can just tell the business people to point AI at terabytes of CSV exports and just ask it questions. That is when it will stop just being labor compression for existing engineers, and start being a world changing paradigm shift.

For now, it's just yet another tool in my toolbelt.

Not sure why the implementation is important or not. The point is the system will be triggered by some text input and complete the task asynchronously on its own.

Right but our company takes on interns not to help the company but to help the intern

> Your terraform written by a person already doesn't have deterministic precision

Can you expand on that? Because it sure seems to me like it is in fact deterministic unless the person deliberately made it otherwise

If i give you a task to write terraform or any code, you won't write what I write, you probably won't even write the same thing twice. You can introduce a bug too, we're not perfect. The output of the task "write some terraform" already isn't deterministic when dealing with people.

Doesn't powershell have structured input and output?

I skimmed some of your comments, You seem to be in the US, at least mid30s, you bought a .dev domain and run your own email? I would think those are possible leads. You really don't think you slipped up once or twice in 5 years of posting? I think an llm would go through all your posts and context of the posts to get. and that would be easier to check if you used any other social media with the same name and see if the accounts have similarities.

I can't tell if this is sarcasm or not

TikTok has a drug-like effect on the brain. Multiple studies show a clear link between excessive TikTok engagement and increased levels of anxiety, depression, and stress. Maybe it is time we regulate it like a drug?

Is that because of engaging with tiktok, or because of the content on tiktok? If the app was exclusively pictures of kittens and nice flowers you saw on your commute, would it have a detrimental effect?

What do you mean exactly, tax it as a vice?!

Hyperbole of some sort. I think it works on both the positive and negative side of the axis too.

I’ll have a packet of cigarettes, a fifth of vodka, and an unrestricted personal electro device.

ID please.

Seems entirely reasonable.

Possibility entirely ineffective, but then again I don’t often see children walking around with bottle a of booze.

It’s about 15 years ahead of its time. Too enlightened for most.

Who fixes the Ai when the Ai is down? Semi serious since they're pretty big on not writing code?

The same guy who used to fix stack overflow, presumably

Maybe network guys can give some hints? I guess they encounter such issue relatively often, when they can't access network equipment by network to fix the network issue. I know management consoles have separate networks on datacenter scale but it isn't that easy with even bigger networks.

I know you say "semi serious" but you can't seriously think there isn't an LLM for internal usage only in Anthropic, right.

I'm not sure what's involved with serving these llms or if the infra could be completely seperate or not for an internal one.

Most ops fixes don’t involve writing code though.

I get the logic, I didn't grow up with my parents youth culture though.

Can't speak to your age or location, but... probably a lot of things you grew up with were part of their childhood too. Disney, Looney Tunes, DC / Marvel, Lord of the Rings, Winnie the Pooh, Star Wars...