← Back to context Comment by omnimus 6 hours ago And what's the difference? 3 comments omnimus Reply esafak 6 hours ago Agents act on their own. If the hammer looked at what you wanted nailed and said, "Sorry, Dave, I can't do that."There are degrees of autonomy, of course, and not all noncompliance is bad. Same as with humans; biological agents. a2ff6eeb0 5 hours ago So, the difference is that you need to delete a few bad training runs? actionfromafar 5 hours ago But it seems much easier to realign an agent until it complies. Or ditch it and grab a new one.
esafak 6 hours ago Agents act on their own. If the hammer looked at what you wanted nailed and said, "Sorry, Dave, I can't do that."There are degrees of autonomy, of course, and not all noncompliance is bad. Same as with humans; biological agents. a2ff6eeb0 5 hours ago So, the difference is that you need to delete a few bad training runs? actionfromafar 5 hours ago But it seems much easier to realign an agent until it complies. Or ditch it and grab a new one.
actionfromafar 5 hours ago But it seems much easier to realign an agent until it complies. Or ditch it and grab a new one.
Agents act on their own. If the hammer looked at what you wanted nailed and said, "Sorry, Dave, I can't do that."
There are degrees of autonomy, of course, and not all noncompliance is bad. Same as with humans; biological agents.
So, the difference is that you need to delete a few bad training runs?
But it seems much easier to realign an agent until it complies. Or ditch it and grab a new one.