I would wait for METR's actual evaluation — '30 hours' is just based on claims of continued effort, not actual successful performance on carefully measured tasks.
We are on an exponential curve - Claude Sonnet 4.5
Hello, I am lost of words honestly. I am feeling a mix of bewilderment, excitement, sadness and gratefulness. Not for this model drop, but for life and this overall development.
A new model just dropped, and it seems like as if this is somehow already twice as fast and large (didn't do the math yet) in autonomous task duration as METR estimated. Probably a lot more.
All I want to say for now is that I am grateful for each and every one of you and for have given me the chance to be part of a community where I did not feel like a black sheep.
Thank you for all of those that are actively trying to make the future go well and the world a bit better. However this continues, I wish you all the love in the world.
Note: This post was crossposted from Planned Obsolescence by the Forum team, with the author's permission. The author may not see or respond to comments on this post.
Subtitle: If acceleration compounds, the naive extrapolation implies superintelligence within a year
This post discusses a public METR report on AI R&D acceler...
TL;DR:
* When we started Rethink Priorities (RP) in 2018, our mission was, simply put, to close the knowledge gaps that stopped people from improving the world as much as they could. That hasn’t changed much, but the landscape we’re doing it in is shifting.
* In 2027, we plan to grow our core GHD, Animal Welfare, and Worldview Investigations teams to take on emerging priorities across causes, including those that the forthcoming transformative AI is creating.
...
This post is part of the Rethink Priorities Cross-Cause Fund (CCF) series on how to allocate funding across causes when it is uncertain what matters most.
...
I would wait for METR's actual evaluation — '30 hours' is just based on claims of continued effort, not actual successful performance on carefully measured tasks.