ankit_mishra

System card linked in the blog post.

> regression on the extremism vision evaluation.

> Relative to their respective GPT-5.6 counterparts, GPT-6 Sol (October) shows a statistically significant regression on standard self-harm, while GPT-6 Luna (October) shows statistically significant regressions on standard self-harm, gore, and sexual content

> "GPT-6 Sol (October) and GPT-6 Luna (October) show an improvement on helpfulness on legitimate requests relative to prior models, though it scores lower on some safety requests"

Concerning how there's significant regressions on so many critical benchmarks, but it is newer and creates UI, so must be good.

It’s crazy that a company can document these safety drops in a PDF, ship the model anyway, and focus the announcement entire on shiny new UI

https://en.wikipedia.org/wiki/Chicken_gun

https://news.ycombinator.com/threads?id=echend

This is an obvious scam, I don't know why I wasted this time double checking.

Makes me sad that this it the top HN post. Also got me thinking if the technique is so effective here (among more-than-average-scam aware community), I don't want to imagine the success rate on other social media.