11
AI agents are here. Here’s what to know about what they can do – and how they can go wrong
(theconversation.com)
this post was submitted on 28 Jul 2025
11 points (100.0% liked)
AI - Artificial intelligence
79 readers
2 users here now
AI related news and articles.
Rules:
- No Videos.
- No self promotion: Don't post links to your articles.
founded 2 months ago
MODERATORS
Now we are beginning to see agents: systems that aspire to greater autonomy and can work in “teams” or use tools to accomplish complex tasks.
Given that an “agent” can be assigned work and carry it out autonomously: no, we are not yet seeing any agents. Every one of these bots requires close attention by a human to weed out the huge quantity of mistakes it generates. That's not an “agent” by any useful definition:
Both Anthropic and OpenAI, for example, prescribe active human supervision to minimise errors and risks.
Right. So, it's a bot which even the vendor recommends you don't leave it to work autonomously. Not an agent.
In other news: “self driving” that requires continuous human monitoring and intervention, by multiple humans per vehicle, is not self driving.
Just because the hype marketing of tech corporations bleats a term into the media, does not mean they've got anything that actually does what they say it does.