Hacker News Reader

Comment by robg | Hacker News Reader

Awesome, predicting words from fMRI has been around for a while and visual cortex can be mapped well.

That said, and coming from a background in neuroimaging 20 years ago, what’s the applicability? MRI hasn’t gotten that much more cost effective for more widespread uses. Magnets are expensive.

View on HN

Yeah, the first thing that comes to mind(har har) when I see this is that we'd be better off trying to develop better scanning technology. You can't exactly walk around town with an MRI strapped to your skull.

We think it could be useful for clinical research and maybe even diagnostics. For example, you could imagine a person with depression(or other neurological disorders) may have a different perception of the same image than a healthy person. Now with the much higher fidelity that both more powerful MRI machines and better generative AI tools can provide, this may now be a very promising direction for future research.

I work in pediatrics and am an academic investigating MRI of kids in various diseases. When I saw this work, I did wonder about us being better able to functionally map where things are going wrong in the pathways of neurodisability. I wondered if this would have applications in being able to do that - for example being able to say that someone could process the image. Do you think it could have this type of application? One thing which would be a deal breaker at the moment is the amount of time participants spend in the scanner. But if we wanted to (for example) see if a child could perceive simple objects, would that be doable do you think?

People with disabilities could benefit greatly from this.

As long as they want to talk about london buses, steam trains, surfing and football.

reading suspect's mind

Reply on news.ycombinator.com