Before all the "it'll misdiagnose someone" comments, remember currently you simply do not get a diagnosis in most cases. Imagine being able to afford sequencing your genome or your kids, but nobody thinks you deserve the time of day to look at it because you don't have the right connections.
tedesign 21 minutes ago [-]
This is extremely disturbing.
PierceJoy 11 minutes ago [-]
In what way?
4 minutes ago [-]
epsteingpt 2 hours ago [-]
This is a heartbreaking story and you can't imagine a more motivated founder.
Godspeed.
ungreased0675 3 hours ago [-]
I’m skeptical that general purpose LLMs are a good fit for a very specialized medical analysis task. Something trained specifically for the task would be the path I’d explore.
dools 11 minutes ago [-]
Does it say anywhere that he’s using general purpose models for the analysis? Fine tuning open weight models is generally available for pretty minimal cost, I’d say his reference to vibe coding is how he is building the software not how the software functions.
boxed 1 hours ago [-]
General models are very cheap to get started with though. So even if they are less than ideal, you can use them to get a company going and then make something more efficient.
9 minutes ago [-]
LoganDark 42 minutes ago [-]
Huh.
> It was clear that something about my approach was interesting.
But no approach.
I do hope the approach pans out. I do understand it must be a trade secret in order for you to have a company but I'm still a little underwhelmed.
andai 17 minutes ago [-]
llm("opus", genome)
Rendered at 06:43:42 GMT+0000 (Coordinated Universal Time) with Vercel.
Godspeed.
> It was clear that something about my approach was interesting.
But no approach.
I do hope the approach pans out. I do understand it must be a trade secret in order for you to have a company but I'm still a little underwhelmed.