And propose the following: "Computer software systems capable of creating context-specific plans in non-deterministic environments." - ThreadSky

About ThreadSky

evijit.io • 20 days ago

And propose the following:

"Computer software systems capable of creating context-specific plans in non-deterministic environments."

Comments

evijit.io•20 days ago

We also break down AI Agents into levels of Agency:

evijit.io•20 days ago

And we posit that Agents have values, that express themselves differently based on the level of agency. For example, tool interoperability may be high in high agency, but consistency may be low:

evijit.io•20 days ago

In fact, when we look at the entire risk-benefit landscape, we find that at the highest level of agency (full autonomy), most values break down and risk > benefit:

evijit.io•20 days ago

Thus, from a purely value laden perspective, we conclude in the paper that highest-level agents should not be deployed, since the values that people seem to care about will largely break down. Some level of human control needs to always be in place.

evijit.io•20 days ago

And that's all folks! This paper is an extension of our (pretty well loved) blog post from last month:
https://huggingface.co/blog/ethics-soc-7

evijit.io•20 days ago

Please do read the full paper! We worked really hard on it. This is, again, the type of paper that can be written forever, but that's not practical, so instead, take what we have and please critically engage with it! 🤗

Looking forward to your thoughts!

https://huggingface.co/papers/2502.02649

Posting Rules

Be respectful to others
No spam or self-promotion
Stay on topic
Follow Bluesky's terms of service

Comments

Posting Rules

Reply