Can you treat AI as a tool?(rybarix.com)
rybarix.com
Can you treat AI as a tool?
https://rybarix.com/tils/ai-anthropo
4 comments
Author here. I understand that you need to prompt in a way that is similar to training set.
It makes sense but it's still weird that your instructions to the machine needs to sound like talking to human. This is just side effect of how is the machine trained and constructed.
It makes sense but it's still weird that your instructions to the machine needs to sound like talking to human. This is just side effect of how is the machine trained and constructed.
Agreed that it is weird. FWIW, when I feel my chat with the LLM has landed (I got a final answer I'm satisfied with), I usually just close the tab or exit the agent session without the ceremony of "thanks, that was helpful."
Anyhow, I feel these entire chats are a gentle game of what to tell, when, and how much. Too little guidance and it won't understand the goal. Too much and it'll drown in details and lose focus. The gestures (which I do try to keep as short as possible) are micro-steerings I apply along the way.
Anyhow, I feel these entire chats are a gentle game of what to tell, when, and how much. Too little guidance and it won't understand the goal. Too much and it'll drown in details and lose focus. The gestures (which I do try to keep as short as possible) are micro-steerings I apply along the way.
Sometimes, maybe? AI was originally created to assist humans as a tool, but it’s evolved into something that blends both technology and emotion—a bit like a mentor, a helper, or even a companion. Instead of arguing about whether AI is “just a tool” or could be conscious, I think it’s more important to focus on how human emotions naturally attach to anything that feels helpful or responsive, whether it’s a living being or not. That’s just human nature.
LLMs are trained to complete threads based on data collected from the internet. Conversations where people say "thank you," "not quite," "we're getting close but..." have different continuation patterns than ones where people are terse or dismissive. These gestures are in the training data, so they will influence how the model continues your thread.
In anything longer than a very short exchange, your tone and feedback signals genuinely help steer the agent in the right direction.