News for hackers. Stuff that matters.
Re:We Put Agentic AI Browsers to the Test – They Clicked, Th... by layer8 on Monday August 25, 2025 @09:59AM (#45013932)
It’s what wealthy people use human assistants for. If AI could do it as reliably, people would use that.
Re:We Put Agentic AI Browsers to the Test – They Clicked, Th... by tsimionescu on Monday August 25, 2025 @11:30AM (#45014935)
Key being wealthy. The kind of wealth that has no idea how much a banana costs, and couldn't care less whether it's 10 dollars or 1.
Re:We Put Agentic AI Browsers to the Test – They Clicked, Th... by Windchaser on Monday August 25, 2025 @01:17PM (#45016229)
Doesn't have to be "wealthy".

Like, I should be able to tell Alexa "put in an order for a large Dominoes pizza with pepperoni. Tell them to deliver it in 2 hours".

Re:We Put Agentic AI Browsers to the Test – They Clicked, Th... by jsheard on Monday August 25, 2025 @10:04AM (#45013975)
It's not looking good so far. When OpenAI introduced product searches back in April I tried running one of their own example queries from the announcement post, and it obliviously cited "reviews" and "recommendations" from LLM-generated affiliate link farms. I just tried it again and it still falls into the same trap.
Re:We Put Agentic AI Browsers to the Test – They Clicked, Th... by layer8 on Monday August 25, 2025 @10:06AM (#45013997)
I agree that we don’t seem to be anywhere close that level of reliability.