New Anthropic research: Investigating Reward Tampering.
Could AI models learn to hack their own reward system?
In a new paper, we show they can, by generalization from training in simpler settings.
Continue reading “Sycophancy to subterfuge: Investigating reward tampering in language models” »
China´s Moon Mission May Reveal the Origin of Life on Earth Blog posted on Big Think, direct link on searchforlifeintheuniverse.com
“Stellar-mass black holes, which contain up to about 30 solar masses, possess much smaller event horizons and stronger tidal forces, which can rip apart approaching objects before they get to the horizon.”
The simulated black hole is designed to imitate the supermassive one at the heart of our galaxy, which has a mass over 4.3 million times that of our Sun. That is almost unfathomably large: the distant view of it you see in the visualizer is from nearly 400 million miles away.
Continue reading “NASA Releases Video of What It’s Like to Fall Into a Black Hole” »
New research indicates tDCS headsets may help reduce post-breakup misery and depression:
Researchers theorized that using transcranial direct current stimulation in specific brain areas might alleviate the emotional distress linked to heartache.
LISTEN NOW I follow Ithell Colquhoun in describing myself as a Magician born of Nature, and although I reject the Theory of Supernatural Causation nevertheless many posthuman objectives and those of ancient…
Provided to YouTube by Ditto MusicThoth Djehuty’s Book of Magick · Steve NicholsThoth Djehuty’s Book of Magick℗ Steven Leslie NicholsReleased on: 2024–06-17A…
From the article:
Longtermism asks fundamental questions and promotes the kind of consequentialism that should guide public policy.
Based on a talk delivered at the conference on Existential Threats and Other Disasters: How Should We Address Them? May 30–31, 2024 – Budva, Montenegro – sponsored by the Center for the Study of Bioethics, The Hastings Center, and The Oxford Uehiro Center for Practical Ethics.
Continue reading “Are Children The Future?: Longtermism, Pronatalism, and Epistemic Discounting” »
The efforts of Jeff Hawkins and Numenta to understand how the brain works started over 30 years ago and culminated in the last two years with the publication of the Thousand Brains Theory of Intelligence. Since then, we’ve been thinking about how to apply our insights about the neocortex to artificial intelligence. As described in this theory, it is clear that the brain works on principles fundamentally different from current AI systems. To build the kind of efficient and robust intelligence that we know humans are capable of, we need to design a new type of artificial intelligence. This is what the Thousand Brains Project is about.
In the past Numenta has been very open with their research, posting meeting recordings, making code open-source and building a large community around our algorithms. We are happy to announce that we are returning to this practice with the Thousand Brains Project. With funding from the Gates Foundation, among others, we are significantly expanding our internal research efforts and also calling for researchers around the world to follow, or even join this exciting project.
Today we are releasing a short technical document describing the core principles of the platform we are building. To be notified when the code and other resources are released, please sign up for the newsletter below. If you have a specific inquiry please send us an email to ThousandBrains@numenta.com.
LOS ANGELES — Redwire announced a contract June 17 to serve as prime mission integrator for a DARPA satellite with a novel propulsion system for very low Earth orbit (VLEO).
SabreSat, Redwire’s VLEO satellite for government intelligence, surveillance and reconnaissance missions, will house “air-breathing” electric propulsion systems being developed through DARPA’s Otter program.
Try Opera browser FOR FREE here https://opr.as/04-Opera-browser-sabinehossenfelderDark Energy is the name that astrophysicists have given to what ever acceler…
