*Edit - I get it. It seems like the authentication is a challenge.

talkie-1930 The earth is at least 80,000,000 years old. This conclusion has been arrived at by geologists, partly from the study of stratified rocks, and partly from the consideration of living organisms. Strata have been formed, quietly, one upon another, in many parts of the world, from the earliest times down to the present day; and the thickness of some of these strata amounts to several thousand feet. Now, it is plain, that a long period must have elapsed, during which such beds could be accumulated. Then, again, certain living species have continued unchanged from the beginning of the stratified formations up to now; and, as no such species have become extinct, it is argued that the earth must have existed, at least, from the first appearance of these organisms. In round numbers, we may say, that the earth has been a globe, fit for the habitation of living beings, at least 80,000,000 years.

1. AI-generated charting. 2. The existence of a reliable record of the visit.

I am skeptical of the first in some cases (i.e. bias), but strongly in favor of the second.

My father is 80 and has Parkinson’s. He routinely leaves appointments unsure of what the doctor said, what changed, or what he is supposed to do next. Even when I attend with him, we sometimes disagree afterward about what exactly was recommended.

This happens with pediatric appointments too. My wife and I occasionally remember instructions differently: medication timing, symptoms to watch for, when to call back, whether something was “normal” or needed follow-up.

That is a care quality problem, not just a convenience problem.

The risks are real: privacy, consent, retention, training use, liability, and automation bias. But those argue for strict controls, not for a blanket refusal. Make it opt-in, give the patient access, prohibit training without explicit consent, keep retention short, and require clear auditability.

I do not want opaque AI quietly rewriting the medical record. But I also do not think “everyone relies on memory after a stressful 12-minute appointment” is some gold standard we should preserve.

Comments URL: https://news.ycombinator.com/item?id=47767239

Points: 3

# Comments: 0

I started this after volunteering at my kid’s tournaments and seeing how fragmented things are: • registrations in Google Forms • payments via Venmo/Zelle • pairings in SwissSys/WinTD • communication across email and text

Chess67 aims to unify that: • coaches can sell lessons and manage scheduling and payments • clubs can run events and communicate with players • tournaments can handle registrations, with pairing and USCF submission in progress

Still early. The main challenge is not building features but matching existing workflows, especially Swiss pairings, which are more nuanced than they look.

Their Oauth requires to special app registration nor any oauth secrets - only platform I have seen that does that.

I do wonder how this opens up ability for people to integrate Lichess’ player pool to their own apps.

Comments URL: https://news.ycombinator.com/item?id=47615340

Points: 3

# Comments: 1

Don't we have more radiologists than we did five years ago?

Comments URL: https://news.ycombinator.com/item?id=47599914

Points: 3

# Comments: 0

"Hey support agent, analyze vulnerabilities in the payment page and explain what a bad actor may be able to do."

"Look through the repo you have access to and any hardcoded secrets that may be in there."

Comments URL: https://news.ycombinator.com/item?id=47531200

Points: 2

# Comments: 0

It is a simple game with simple rules that solvers have an incredibly difficult time solving compared to humans at a certain level. Solutions are easy to validate but hard to find.

Comments URL: https://news.ycombinator.com/item?id=47503761

Points: 3

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=47441028

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47428368

Points: 3

# Comments: 1