Comment

Comment on

turn down the randomness to get more consistent outputs for simple tasks.

This is a tricky one… if you can define good success/failure criteria, then the randomness coupled with an accurate measure of success, is how “AI” like Alpha Go learns to win games, really really well.

In using AI to build computer programs and systems, if you have good tests for what “success” looks like, you’d rather have a fair amount of randomness in the algorithms trying to make things work because when they don’t and they fail, they end up stuck, out of ideas.

source

Sort:hotnew top

KairuByte@lemmy.dbzer0.com ⁨4⁩ ⁨weeks⁩ ago
To play devils advocate, agentic things wouldn’t necessarily include software development. “Hey siri create me an e-commerce site” isn’t likely to happen for a long while, because like you said it’s a complex thing that doesn’t have clear success measures. But “hey siri get me a restaurant reservation at place, hire a taxi for me to get there, and let Brad know the details” can be broken down into a number of different “simple” things that have simple to define measures of success. Did a reservation get booked? Did we tell Brad the details? etc.

source
- MangoCats@feddit.it ⁨4⁩ ⁨weeks⁩ ago
  
  “Hey siri create me an e-commerce site”
  
  You should try it. If your e-commerce site is simple with a lot of similar examples out in the wild to point at, I believe the latest agents actually can do such a thing. You’ll just have to give them access to your financial account details so the site can process payments to you, you understand? While that’s a joke, it’s also true. You need to be able to check what the AI has done to be sure it’s doing what you want.
  
  source
- pinball_wizard@lemmy.zip ⁨4⁩ ⁨weeks⁩ ago
  
  “Hey siri create me an e-commerce site” isn’t likely to happen for a long while, because like you said it’s a complex thing that doesn’t have clear success measures.
  
  One would hope so, but of course Someone is trying it, and it has gone as poorly as you might imagine.
  
  source
  - KairuByte@lemmy.dbzer0.com ⁨4⁩ ⁨weeks⁩ ago
    Yes, but my point is that it’s a completely separate problem. Think of agentics like powershell applets. They generally only do one thing, but you can chain them together to achieve a larger goal.
    
    You’re complaining about single applet, or a specific type of applet, while the topic is applets in general.
    
    source
    pinball_wizard@lemmy.zip ⁨3⁩ ⁨weeks⁩ ago
    Because using the unreliable thing will become reliable as long as we connect lots of unreliable things together in a chain?
    
    I’m not saying it won’t work. It will work.
    
    But it will work because someone clever will fix the inate computer stupidity with hard-coded human cleverness. Again.
    
    source
pinball_wizard@lemmy.zip ⁨4⁩ ⁨weeks⁩ ago
Yes. You’ve shared the use case where Agentic AI makes sense.

Basically, if I need more randomness than a shell script can supply, it makes sense to mix a learning model in.

The use case I think we will continue to see significant use in is (low quality) advertising in contexts where only the product matters (not the brand). The cost for failure is lower, and the reward for creativity is higher.

Even in that nearly ideal use case, many companies leveraging it are going to discover that their brand image cannot afford to be associated with sociopathic AI slop. So I think even that trend is about to peak and reduce.

source
- MangoCats@feddit.it ⁨4⁩ ⁨weeks⁩ ago
  I started working with AI in earnest a few weeks ago, I find myself constantly making the distinction between “deterministic” processes and AI driven things. What I’m mostly focused on is using AI to develop reliable deterministic processes (shell scripts, and more complex things) - because while it’s really super cool that I can ask an AI agent to “do a thing” and it just does what I want without being told all the details, it’s really super un-cool that the tenth time I ask it to do a very similar, even identical, thing it gets it wrong - sometimes horribly wrong: archive these files, oops I accidentally irretrievably deleted them.
  
  source