Entirely Foreseeable AWS Outageshttps://rys.io/en/182.html
-
@rysiek I 100% agree. Any sane #Sysadmin/#DevOps person would far prefer a deterministic tool to a non-deterministic tool. Science has everything to do with finding that which is reliable and deterministic, and can be trusted, used as a basis, used as a foundation to build higher, more trust-worthy things. It all comes back to trust at the end of the day - *not* saving time learning difficult things, *not* eschewing doing things "the hard way", *not* taking shortcuts.
@Owl Eyes Yes, but also a bit no.
On one hand you want your tools to be deterministic and predictable. On the other hand, people aren't deterministic either, and they are the most valuable tools
Maybe in time these agentic tools become predictable enough to be used as sysadmin's grease monkeys, but my experience so far is that I can't let it do its job without my constant vigilant supervision.
@Michał "rysiek" Woźniak ·
-
@Owl Eyes Yes, but also a bit no.
On one hand you want your tools to be deterministic and predictable. On the other hand, people aren't deterministic either, and they are the most valuable tools
Maybe in time these agentic tools become predictable enough to be used as sysadmin's grease monkeys, but my experience so far is that I can't let it do its job without my constant vigilant supervision.
@Michał "rysiek" Woźniak ·@hans I agree people are precious and unique - and also super non-deterministic.
I think AI can be most effectively used to stimulate new thinking, and make bold forays into new-to-oneself domains of knowledge. The LLMs can reveal lots of new terminology, and possibilities one didn't think to search for before. But then one has to take one's time, verifying the claims (often wrong), and synthesize a truth for oneself, going beyond the hallucination of the LLMs. So I think of LLMs/agents more like *discovery* tools, at best, but much less something to build solid foundations with.
-
Entirely Foreseeable AWS Outages
https://rys.io/en/182.htmlOnce you strip away the marketing hype, agentic systems like Kiro AI are just automation tools.
The difference between Kiro and regular infrastructure management tools is that the latter are deterministic. They can be tested, analyzed, and bugs can be reliably, provably fixed.
That's just not the case with agentic tools. They are by their very nature non-deterministic. And that's the last thing a systems engineer should want.
@rysiek How do you funnel suckers, I mean, errr... investors, into "deterministic tools we've been using for decades", though?
-
-
@hans I agree people are precious and unique - and also super non-deterministic.
I think AI can be most effectively used to stimulate new thinking, and make bold forays into new-to-oneself domains of knowledge. The LLMs can reveal lots of new terminology, and possibilities one didn't think to search for before. But then one has to take one's time, verifying the claims (often wrong), and synthesize a truth for oneself, going beyond the hallucination of the LLMs. So I think of LLMs/agents more like *discovery* tools, at best, but much less something to build solid foundations with.
@Owl Eyes That's my experience so far, indeed. But the new knowledge that my tool has brought me, is more often than not wrong.
It has no problem telling me to configure settings that don't exist, even after I tell it they don't exist.
So far, it has been an interesting journey, but hasn't saved me any time. In fact, I have spent a lot more time, because I had to explain to my agent what I wanted, and go on a wild goose chase afterwards to check its solutions.
But I kind of expect that in a few years, these tools will become good enough to actually help. -
@Michał "rysiek" Woźniak · I'm a sysadmin myself, so I can call them tools
But agree: at the moment these agentic tools aren't good enough to be trusted with massive, complex tasks. But I would be surprised if that would remain the situation for long. -
@Michał "rysiek" Woźniak · I'm a sysadmin myself, so I can call them tools
But agree: at the moment these agentic tools aren't good enough to be trusted with massive, complex tasks. But I would be surprised if that would remain the situation for long.@hans I would be surprised if it ever meaningfully changes.
-
Entirely Foreseeable AWS Outages
https://rys.io/en/182.htmlOnce you strip away the marketing hype, agentic systems like Kiro AI are just automation tools.
The difference between Kiro and regular infrastructure management tools is that the latter are deterministic. They can be tested, analyzed, and bugs can be reliably, provably fixed.
That's just not the case with agentic tools. They are by their very nature non-deterministic. And that's the last thing a systems engineer should want.
Pfft, please. Engineers. They're so unreasonable.
What are engineers looking for? Precision?
-
Entirely Foreseeable AWS Outages
https://rys.io/en/182.htmlOnce you strip away the marketing hype, agentic systems like Kiro AI are just automation tools.
The difference between Kiro and regular infrastructure management tools is that the latter are deterministic. They can be tested, analyzed, and bugs can be reliably, provably fixed.
That's just not the case with agentic tools. They are by their very nature non-deterministic. And that's the last thing a systems engineer should want.
@rysiek It’s not that they are non-deterministic - they actually aren’t. Same input will generate the same output as long as you configure it not to perform random sampling or bind the random number generator to a stable input.
The problem with these tools is that they are unpredictable. You cannot reason about their output beforehand. Nor can you reason about the effect changes to inputs are gonna have on the outputs.
That’s not non-determinism, that’s chaos.
-
@rysiek It’s not that they are non-deterministic - they actually aren’t. Same input will generate the same output as long as you configure it not to perform random sampling or bind the random number generator to a stable input.
The problem with these tools is that they are unpredictable. You cannot reason about their output beforehand. Nor can you reason about the effect changes to inputs are gonna have on the outputs.
That’s not non-determinism, that’s chaos.
@slotos if we want to be nit picky, sure why not – these models use random seeds while generating their output.
So while *technically* you are correct (the best kind of correct!) that if all inputs are exactly the same, the outputs will be the same as well, from the perspective of these systems as they are being used bye people using them, they are non-deterministic, because these users have no control over the random seed.
-
R ActivityRelay shared this topic
