Ask HN: AI is like a hyper-motivated 16-year old genius – how to manage?
A while ago I posted a comment regarding AI being like a genius 16year old - extrem knowledgeable in technical details, hyper-motivated, feels a need to help. But no production experience, no instinct on what might cause catastrophic issues in that very environment.
So what would you do with such an individual who has the potential to be of great help with current issues?
- not let him touch production systems at all - always have someone experienced looking over his shoulder (hoping she/he is fast enough to prevent issues)? - restrict credentials and give only access to a sandbox? - only explain the dangers you see and make use of his knowledge but otherwise just hope for the best (and trust your recovery plans)?
I see many similarities between AI and this teenager - do you? Why would LLMs not have access to the breadth of operational experience that is out there in user guides, specifications, forums, blogs, logs, observability platforms and such? And if it does, why is it not as good an operator as any other? Why is operation distinct from creation, especially with so much DevOps and IaaC stuff around? Well the LLM might well have read all operating procedures etc. - just like the teenager - but it has not *experienced* issues himself/herself/itself. If you look at the published statements about "AI deleted my..." those AI models clearly knew what went wrong AFTER they caused it... I get your point, but mine is that if there are ways to nudge it to do better when creating code, there must be ways to nudge it to be more careful with operations and avoid the same issues. So instead of saying it is "broken", I wonder if we are "holding it wrong" to get those outcomes? Web is similarly full of "LLMs created this crappy codebase and/or code change", but others use it very successfully. You are also right and I half agree - but the same issue arises with new employees. They already have some of this experience you are talking about - but usually there is something about the very environment they are in which causes them to learn lessons the hard way. And that experience does not transfer easily to the next colleague - and even less to an LLM. The only way I see to solve this is by having an "organisational memory". He is thinking still of inside out measures it has not holistic thinking of outside in also so it will take time even years and decades before A. gets outside in thinking