[gassi]

> In a world where we can type anything into a text box and get the information back instantly we are circumventing the need to visit websites altogether.

This is purely anecdotal, but the only people in my extended circle making this transition (to any extent) are the technically savvy; everyone else is slowly realizing how awful AI tools and "AI-first experiences" can be and are actively trying to avoid them.

[nvader]

I've noticed this bimodal distribution of perception too, and my hypothesis is that's it's hugely driven by the difference of "who is in the driver's seat".

Your tech-savvy AI early adopters are discerning between tools, the deployments and environments, and are willing and able to change things to extract the highest output from current capabilities. For instance, re-architecting a codebase to make it easier for agents to contribute to it.

The rest are having AI hypeware shoved upon them, often as a cost cutting measure, and lack the agency to influence outcomes. When agents misbehave, they only have the option to "Press 0 to speak with a Human" and hope that works.

I suspect this is a big factor in the divide we're seeing, and might result in your median adult being ambushed by recent gains in capabilities.

[coliveira]

I'm technical, and I use AI tools but only for basic technical tasks such as finding information, summarizing simple topics, etc. For everything else AI is too inconsistent/inconvenient/unnatural. While it works fine as a demo, real world applications of AI are still far from anything useful in most areas.

[CuriouslyC]

AI in apps is garbage. Cheap, low quality models and inflexible interaction patterns.

AI agents using frontier models, configured nicely, that interact with programs that have APIs are pure gold.

[dfdsf2]

I read the first line and thought - this guy gets it.

The read the second line and erm.... maybe not. The whole Agents thing has been pushed for almost a year now and it hasn't disrupted the profession of engineers on a noticeable scale.