Comment by antirez
1 day ago
> You can't prompt 99.95% uptime on Black Friday. Neither can you prompt your way to keeping a site secure, updated, and running.
This is completely wrong. Agents will not just be able to write code, like they do now, but will also be able to handle operations, security, continuing to check, and improve the systems, tirelessly.
And someday we will have truly autonomous driving cars, we will cure cancer, and humans will visit Mars.
You can't prompt this today, are you suggesting this might come literally tomorrow? 10 years? 30? At that unknown time will your comment become relevant?
the quoted comment is arguing that devops will never be promptable — putting aside the discussion about whether or not that's true today, the argument here is that it's not likely to _never_ be possible
I'm working on a project now and what you're saying is already true. I have agents that are able to handle other things apart from code.
But these are MY agents. They are given access to MY domain knowledge in the way that I configured. They have rules as defined by ME over the course of multi-week research and decision making. And the interaction between my agents is also defined and enforced by me.
Can someone come up with a god-agent that will do all of this? Probably. Is it going to work in practice? Highly unlikely.
So you think a statement about the current state of things is wrong because you believe that sometime in the future agents are going to magically do everything? Great argument!
To be able to do this requires perfect domain knowledge AND environment knowledge AND be able to think deeply about logical dominoes (event propagation through the system, you know, the small stuff that crashes cloudflare for the entire planet for example).
Please wake me up when Shopify lets a bunch of agentic LLMs run their backends without human control and constant supervision.
The extreme here is thinking machines will do everything. The reality is likely far closer to less humans being needed.