you are viewing a single comment's thread
view the rest of the comments
[+] -17 points 1 year ago (10 children)

AI is a tool and like all tools, it depends on how you use it and who uses it. Not everybody's a software engineer. I talked to a software architect who was very happy about AI agents because they could design and architect a solution and let it be implemented right there. They didn't need a software engineer (their words).

Just because you use an AI agent doesn't make you dumber or make you turn off your mind. After being encouraged to use AI agents at work, I'm come to appreciate that even with them there are vastly different levels of usage.

  • source
  • hideshow 10 child comments
  • [–] 8 points 1 year ago (9 children)

    You still need a software engineer to review the code. It's naive to think that randomly generated code will work, and by "work" i mean not just do what it's supposed to, but also handle edge cases and be secure.

  • source
  • parent
  • hideshow 9 child comments
  • [+] -11 points 1 year ago (8 children)

    If you think it's random, you don't understand LLMs.

  • source
  • parent
  • hideshow 8 child comments
  • [–] 4 points 1 year ago (7 children)

    So, in your learned opinion, it's deterministic?

  • source
  • parent
  • hideshow 7 child comments
  • [–] 1 point 1 year ago (3 children)

    You sent me down a bit of a rabbit hole, but it turned up an interesting answer. Turns out they are nondeterministic, and why they aren't deterministic is still an open question https://thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference/

  • source
  • parent
  • hideshow 3 child comments
  • [+] -6 points 1 year ago (2 children)

    And you are perfectly deterministic? Because if you aren't, by your own dichotomic logic, you're random too.

  • source
  • parent
  • hideshow 2 child comments