AI Provably Safe

“AI Risk=Jenga” For Humanity, An AI Safety Podcast Episode #17, Liron Shapira Interview

Peter A. Jensen2024-02-28T23:29:46+00:00February 28, 2024|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

URGENT AND WORTH YOUR TIME. Please Look Up: For Humanity, An AI Safety Podcast Episode #1

Peter A. Jensen2024-02-26T23:17:55+00:00February 26, 2024|

URGENT AND WORTH YOUR TIME. [...]

For Humanity Podcast. The Interpretability Problem: For Humanity, An AI Safety Podcast Episode #3. 14 NOV.

Peter A. Jensen2024-02-29T22:24:19+00:00February 26, 2024|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

12 years ago. NBC NEWS. Control dangerous AI before it controls us, one expert says. Super-intelligent computers or robots have threatened humanity’s existence more than once in science fiction. Such doomsday scenarios could be prevented if humans can create a virtual prison to contain artificial intelligence before it grows dangerously self-aware. 1 MAR 2012.

Peter A. Jensen2024-02-26T18:17:30+00:00February 26, 2024|

NBC NEWS. Control dangerous AI before it controls us, [...]

Demis Hassabis on Chatbots to AGI | EP 71. “Demis, what’s your P(Doom)?” Demis: “definitely non-zero” 23 FEB

Peter A. Jensen2024-02-26T11:06:24+00:00February 26, 2024|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

CNBC. Richard Branson and Oppenheimer’s grandson urge action to stop AI and climate ‘catastrophe’. 15 FEB.

Peter A. Jensen2024-02-18T12:41:55+00:00February 18, 2024|

More precisely, "Safety Engineering" is the solution for Safe [...]

Geoffrey Hinton | Will digital intelligence replace biological intelligence? 2 FEB

Peter A. Jensen2024-02-22T10:27:15+00:00February 2, 2024|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

Yuval Noah Harari. “Humans were always far better at inventing tools than using them wisely.”

Peter A. Jensen2024-02-19T14:00:50+00:00February 1, 2024|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

Artificial intelligence ‘godfather’ Yoshua Bengio opens up about his hopes and concerns. 29 JAN.

Peter A. Jensen2024-02-22T10:07:36+00:00January 29, 2024|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

PREDICTION [opinion]. Within 10 years 70-80% of current G20 manual & knowledge worker jobs will be: (A) manually automated by physical robots, or (B) digitally automated by AGI

Peter A. Jensen2024-01-22T12:04:44+00:00January 22, 2024|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

CNBC. DAVOS 2024. We don’t want to see an AI ‘Hiroshima,’ Salesforce CEO warns.

Peter A. Jensen2024-01-21T21:50:15+00:00January 17, 2024|

A very good read from a respected source! [...]

SCIENTIFIC AMERICAN. Opinion. AI Safety Research Only Enables the Dangers of Runaway Superintelligence. AI will become inscrutable and uncontrollable. We need to stop AI development until we have a necessary safety conversation. 09 JAN.

Peter A. Jensen2024-01-10T10:32:26+00:00January 10, 2024|

A very good read from a respected source! (with [...]

REPORT. On the Controllability of Artificial Intelligence: An Analysis of Limitations. Roman V. Yampolskiy. 2022-05-25.

Peter A. Jensen2024-01-10T10:22:06+00:00January 10, 2024|

A very important read from a very respected and [...]

U.S. ARTIFICIAL INTELLIGENCE SAFETY INSTITUTE by NIST

Peter A. Jensen2024-01-14T21:29:31+00:00January 1, 2024|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

EDITORIAL (opinion) 5 minute read. Thoughts and questions for our last weekend of 2023… about fear and love, humanity and AGI/ASI.

Peter A. Jensen2024-01-03T12:06:59+00:00December 30, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

WIRED. How Not to Be Stupid About AI, With Yann LeCun. It’ll take over the world. It won’t subjugate humans. For Meta’s chief AI scientist, both things are true. 22 DEC.

Peter A. Jensen2023-12-26T04:43:28+00:00December 22, 2023|

A very good read from a respected source! [...]

STEVE OMOHUNDRO. PROVABLY SAFE AGI – MIT MECHANISTIC INTERPRETABILITY CONFERENCE – MAY 7, 2023

Peter A. Jensen2023-12-02T20:32:56+00:00December 2, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

TOP-20 AGI Problems and TOP-20 Known AGI Mathematically Provable Containment and Control Solutions (alphabetical). Source. LESSWRONG

Peter A. Jensen2023-12-08T20:33:33+00:00December 2, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

AI ALIGNMENT FORUM. An Important RESOURCE aligned with LESSWRONG.

Peter A. Jensen2023-12-02T21:16:43+00:00December 2, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

How to Keep AI Under Control | Max Tegmark | TED

Peter A. Jensen2023-12-05T05:37:59+00:00November 26, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

Teach AI like we teach our children. (But, AI must be contained always and forever.) Sponsored by SafeAI Forever.

Peter A. Jensen2024-03-30T17:15:23+00:00November 26, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

The Interpretability Problem: For Humanity, An AI Safety Podcast Episode #3

Peter A. Jensen2024-02-26T23:13:53+00:00November 14, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

Managing AI Risks in an Era of Rapid Progress. Bengio et al. 12 NOV.

Peter A. Jensen2023-11-26T15:17:45+00:00November 12, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

The Dark Side of Competition in AI | Liv Boeree | TED. “Don’t hate the players. Change the game.”

Peter A. Jensen2024-03-05T00:19:25+00:00November 9, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

THE GUARDIAN. Ilya: the AI scientist shaping the world.

Peter A. Jensen2023-11-19T12:02:35+00:00November 2, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

Existential Risk Observatory. AI Summit Talks featuring Professor Stuart Russell. 31 OCT 2023.

Peter A. Jensen2023-11-02T02:17:53+00:00October 31, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

Existential Risk Observatory. Reducing human extinction risks by informing the public debate.

Peter A. Jensen2023-10-30T07:15:08+00:00October 30, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

Superintelligence (2014) bestseller by Nick Bostrom with Book Reviews [and 4 possible methods to Control Superintelligence]

Peter A. Jensen2023-10-18T13:07:07+00:00October 16, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

Existential Risk Observatory. Does interpretability change everything? 07 OCT 2023.

Peter A. Jensen2023-10-30T07:37:00+00:00October 7, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

REPORT. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! 05 OCT.

Peter A. Jensen2023-11-29T11:13:50+00:00October 5, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

AP. Don’t expect quick fixes in ‘red-teaming’ of AI models. Security was an afterthought. 13 AUG 2023. BY FRANK BAJAK

Peter A. Jensen2023-10-05T08:47:14+00:00August 13, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

MICROSOFT. Microsoft AI Red Team building future of safer AI. 07 AUG 2023.

Peter A. Jensen2023-10-05T08:49:41+00:00August 7, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

LLM Attacks. Universal and Transferable Adversarial Attacks on Aligned Language Models. JULY 2023.

Peter A. Jensen2023-10-05T08:58:38+00:00August 1, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

Will Superintelligent AI End the World? | Eliezer Yudkowsky | TED

Peter A. Jensen2024-02-26T04:06:31+00:00July 11, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

OpenAI. Introducing Superalignment. 05 JULY 2023.

Peter A. Jensen2023-10-06T05:32:44+00:00July 5, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

“PROBABLY NOT”? GPT-4 System Card: “Finally, we facilitated a preliminary model evaluation by the Alignment Research Center (ARC) of GPT-4’s ability to carry out actions to autonomously replicate (5) and gather resources—a risk that, while speculative, may become possible with sufficiently advanced AI systems—with the conclusion that the current model is probably not yet capable of autonomously doing so.”

Peter A. Jensen2023-10-05T10:21:45+00:00June 8, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

THE VERGE. AI startup Anthropic wants to write a new constitution for safe AI. MAY 09, 2023

Peter A. Jensen2023-11-26T08:12:04+00:00May 9, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

John Henry Clippinger. What is Intelligence ? Machine – Natural – Human – Ethical. March 1, 2023. Linkedin.

Peter A. Jensen2023-10-20T17:49:44+00:00March 1, 2023|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

ANTHROPIC. Predictability and Surprise in Large Generative Models. 03 OCT 2023

Peter A. Jensen2023-11-26T08:12:45+00:00October 3, 2022|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

Artificial Superintelligence: A Futuristic Approach by Roman V. Yampolskiy (2016)

Peter A. Jensen2024-02-25T21:16:31+00:00December 31, 2016|

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. [...]

Load More Posts

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT.

IMPORTANT COPYRIGHT DISCLAIMER. THIS AI SAFETY BLOG IS FOR EDUCATIONAL PURPOSES ONLY AND KNOWLEDGE SHARING IN THE GENERAL PUBLIC INTEREST ONLY. This free and open not-for-profit ‘First do no harm.’ AI-safety blog is curated and organised by BiocommAI. Some of the following selected stand-out information is copyrighted and is CITED WITH LINK-OUT to the respective publisher sources. These vital public interest stories are selected and presented to serve the global public humanitarian interest for educational and knowledge sharing purposes regarding the EXISTENTIAL THREAT TO HUMANITY OF THE PROLIFERATION OF UNCONTROLLED, UNCONTAINED, UNSAFE AND UNREGULATED AI TECHNOLOGY. Copyrights owned by publishing sources are respectfully cited by the LINK-OUT to all sources. To request a takedown or update please contact: info@biocomm.ai

Copyright 2023 | All Rights Reserved | BiocommAI Limited | 1st Floor, 9 Exchange Place, IFSC, Dublin 1, D01 X8H2, Ireland