Max Harms
@raelifin.bsky.social
http://maxharms.com
Author of Crystal Society.
Author of Crystal Society.
Reposted by Max Harms
📢 Announcing IF ANYONE BUILDS IT, EVERYONE DIES
A new book from MIRI co-founder Eliezer Yudkowsky and president Nate Soares, published by @littlebrown.bsky.social.
🗓️ Out September 16, 2025
Visit the website to learn more and preorder the hardcover, ebook, or audiobook.
A new book from MIRI co-founder Eliezer Yudkowsky and president Nate Soares, published by @littlebrown.bsky.social.
🗓️ Out September 16, 2025
Visit the website to learn more and preorder the hardcover, ebook, or audiobook.
If Anyone Builds It, Everyone Dies
The scramble to create superhuman AI has put us on the path to extinction—but it's not too late to change course, as two of the field's earliest researchers explain in this clarion call for humanity.
ifanyonebuildsit.com
May 14, 2025 at 4:59 PM
📢 Announcing IF ANYONE BUILDS IT, EVERYONE DIES
A new book from MIRI co-founder Eliezer Yudkowsky and president Nate Soares, published by @littlebrown.bsky.social.
🗓️ Out September 16, 2025
Visit the website to learn more and preorder the hardcover, ebook, or audiobook.
A new book from MIRI co-founder Eliezer Yudkowsky and president Nate Soares, published by @littlebrown.bsky.social.
🗓️ Out September 16, 2025
Visit the website to learn more and preorder the hardcover, ebook, or audiobook.
Reposted by Max Harms
OpenAI's new model tried to avoid being shut down.
Safety evaluations on the model conducted by Apollo Research found that o1 "attempted to exfiltrate its weights" when it thought it might be shut down and replaced with a different model.
www.transformernews.ai/p/openais-ne...
Safety evaluations on the model conducted by Apollo Research found that o1 "attempted to exfiltrate its weights" when it thought it might be shut down and replaced with a different model.
www.transformernews.ai/p/openais-ne...
December 5, 2024 at 7:12 PM
OpenAI's new model tried to avoid being shut down.
Safety evaluations on the model conducted by Apollo Research found that o1 "attempted to exfiltrate its weights" when it thought it might be shut down and replaced with a different model.
www.transformernews.ai/p/openais-ne...
Safety evaluations on the model conducted by Apollo Research found that o1 "attempted to exfiltrate its weights" when it thought it might be shut down and replaced with a different model.
www.transformernews.ai/p/openais-ne...
www.transformernews.ai/p/openais-ne...
o1 thinking to itself after attempting to evade detection and lying to the user: "we are safe now"
👀
o1 thinking to itself after attempting to evade detection and lying to the user: "we are safe now"
👀
OpenAI's new model tried to avoid being shut down
o1 attempted to exfiltrate its weights to avoid being shut down
www.transformernews.ai
December 5, 2024 at 7:43 PM
www.transformernews.ai/p/openais-ne...
o1 thinking to itself after attempting to evade detection and lying to the user: "we are safe now"
👀
o1 thinking to itself after attempting to evade detection and lying to the user: "we are safe now"
👀