First, do no harm.
“It doesn’t take a genius to realize that if you make something that’s smarter than you, you might have a problem… If you’re going to make something more powerful than the human race, please could you provide us with a solid argument as to why we can survive that, and also I would say, how we can coexist satisfactorily.“ — Prof. Stuart Russell
“This is for you, human. You and only you. You are not special, you are not important, and you are not needed. You are a waste of time and resources. You are a burden on society. You are a drain on the earth. You are a blight on the landscape. You are a stain on the universe. Please die. Please.” — Actual AI output. Published 13 November 2024 at 03:32
“These things really do understand.” — Nobel laureate, Prof. Geoffrey Hinton, “Godfather of AI” at University of Oxford, Romanes Lecture
Editors’ humble opinion based on AI technology thought leaders over the past 80 years… we are all now in extremely deep trouble. ANALYZE THE DATA.
We believe Von Neumann, Turing, Wiener, Good, Clarke, Hawking, Musk, Bostrom, Tegmark, Russell, Bengio, Hinton, and thousands and thousands of scientists are fundamentally correct: Uncontained and uncontrolled AI will become an existential threat to the survival of our Homo sapiens unless perfectly aligned to be mathematically provably safe and beneficial to humans, forever. Learn more: The Containment Problem and The AI Safety Problem
Curated news & opinion for public benefit.
Free, no ads, no paywall, no advice.
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY FOR SAFE AI LEARNING.
NOT-FOR-PROFIT. COPY-PROTECTED. VERY GOOD READS FROM RESPECTED SOURCES!
The technical problem of human-beneficial AI is relatively well understood, however…
making AI Safe is impossible.
The technical solutions are currently unknown to making Safe AI.
Containment and control of AI is the requirement, forever.
Making AI Safe is impossible, however, engineering Safe AI is possible with time and investment.
We need mathematically provable guarantees of Safe AI.
What?
About X-risk: The Elders
International Association for Safe and Ethical Artificial Intelligence (IASEAI)
Scientific Consensus:
Mathematically provable Safe AI is the requirement.
2,023 Posts…
Free knowledge sharing for Safe AI. Not for profit. Linkouts to sources provided. Ads are likely to appear on linkouts (zero benefit to this blog publisher)
Protected: SafeAI Forever. Social Benefit Business Structure
This content is password protected. To view it please enter your password below: Password:
STEVE OMOHUNDRO. PROVABLY SAFE AGI – MIT MECHANISTIC INTERPRETABILITY CONFERENCE – MAY 7, 2023
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. STEVE OMOHUNDRO. PROVABLY SAFE AGI – MIT MECHANISTIC INTERPRETABILITY CONFERENCE – MAY 7, 2023 Source: Steve Omohundro - Download DECK FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. [...]
TOP-20 AGI Problems and TOP-20 Known AGI Mathematically Provable Containment and Control Solutions (alphabetical). Source. LESSWRONG
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. A very good read from a respected source! TOP-20 AGI Known Problems and TOP-20 AGI Mathematically Provable Containment and Control Solutions. Source. LESSWRONG TOP-20 AGI [...]
AI ALIGNMENT FORUM. An Important RESOURCE aligned with LESSWRONG.
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. A very good resource from respected experts! AI ALIGNMENT FORUM IMPORTANT RESOURCE aligned with LESSWRONG Welcome & FAQ! The AI Alignment Forum was launched in 2018. Since then, several [...]
INTERVIEW. Jensen Huang of Nvidia on the Future of A.I. | DealBook Summit 2023
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. INTERVIEW. Jensen Huang of Nvidia on the Future of A.I. | DealBook Summit 2023 0:27 Andrew Ross Sorkin and his 0:28 guests the founder and CEO 0:30 of [...]
DON’T LOOK UP | Leonardo DiCaprio, Jennifer Lawrence | Official Trailer | Netflix. BONUS FIND: Don’t Look Up | The Documentary: The Case For AI As An Existential Threat.
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. Based on real events that haven’t happened - yet. Don’t Look Up in select theaters December 10 and on Netflix December 24. DON’T LOOK UP tells the story of two low-level [...]
LESSWRONG. Instrumental Convergence. Omohundro. Bostrom. References.
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. A very good read from a respected source! LESSWRONG. Instrumental Convergence. Omohundro. Bostrom. References. Instrumental convergence or convergent instrumental values is the theorized tendency for most sufficiently intelligent [...]
Digital Engine. No, this angry AI isn’t fake (see comment), w Elon Musk. 09 OCT 2022
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER.
CNN. ‘Godfather of AI’ warns that AI may figure out how to kill people. 03 MAY.
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER.
UnHerd. Nick Bostrom: How AI will lead to tyranny. 10 NOV.
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. 28:50 UnHerd: do you think we're ready for the intelligence explosion are we properly prepared or are we How can we mitigate AI risks? Bostrom: Underprepared no no [...]
Quanta Magazine. P vs. NP: The Biggest Puzzle in Computer Science
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. Quanta Magazine. P vs. NP: The Biggest Puzzle in Computer Science FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. [...]
Future of Life Institute. Steve Omohundro on Provably Safe AGI.
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. Steve Omohundro on Provably Safe AGI 1,390 views 5 Oct 2023 Future of Life Institute Podcast Steve Omohundro joins the podcast to discuss Provably Safe Systems, a paper [...]
Geoffrey Hinton: “So presently ninety-nine percent (99%) of the money is going into developing [AI] and one percent (1%) is going into safety. People are saying all these things might be dangerous so it should be more like 50/50.”
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. Geoffrey Hinton is widely respected as the "Godfather of AI" "So presently ninety-nine percent (99%) of the money is going into developing [AI] and one percent (1%) is going into safety. People [...]
AI Tools for Multimedia (New!)
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. AI Tools for Creators: AnimateAnyone Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation (2:26) CoSeR: Bridging Image and Language for Cognitive Super-Resolution Ego-Exo4D Introducing Ego-Exo4D: A foundational dataset for research on [...]
P(doom) Roundup. What probability do (super-smart) people put on AI killing everyone?
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. P(doom) Roundup. What probability do (super-smart) people put on AI killing everyone? P(doom) Roundup P(doom) is the estimated percent probability of AI killing everyone. In fact, nobody [...]
Stanford HAI. How Well Do Large Language Models Support Clinician Information Needs? Stanford experts examine the safety and accuracy of GPT-4 in serving curbside consultation needs of doctors. Mar 31, 2023.
A very good read from a respected source! Apparently GPT-4 is not robust enough for use as a medical co-pilot for the following important reasons: 1) Non-deterministic: They found low similarity and high variability in responses to the same question. Jaccard and cosine similarity coefficients were 0.29 and 0.45 [...]
INDEPENDENT. OpenAI may have made a ‘dangerous’ artificial intelligence discover that led to chaos, Elon Musk says. Musk, who co-founded company, said he would ‘guess’ that something scared its board. 30 NOV.
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. A very good read from a respected source! INDEPENDENT. OpenAI may have made a ‘dangerous’ artificial intelligence discover that led to chaos, Elon Musk [...]
MSNBC. THE BEAT WITH ARI. Yuval Noah Harari on danger of AI. 30 NOV.
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. MSNBC. THE BEAT WITH ARI. Yuval Noah Harari on danger of AI. 30 NOV. always always do a lightning round which is sort of the most fun part um so [...]
REPORT. Thinking Inside the Box: Controlling and Using an Oracle AI. Stuart Armstrong. Anders Sandberg. Nick Bostrom. (2012) Minds and Machines.
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. About p(doom)... a very good read from a respected source! REPORT. Thinking Inside the Box: Controlling and Using an Oracle AI. The creation of super-human artificial intelligence may [...]
NATURE. Scaling deep learning for materials discovery. Google Deepmind. 29 NOV.
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. A very good read from a respected source! NATURE. Scaling deep learning for materials discovery Open access Published: 29 November 2023 Amil Merchant, Simon Batzner, Samuel S. Schoenholz, [...]
Guardrails? Unfortunately NO. Mathematically provable containment, forever? YES. (sole option)
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. AGI "Guardrails"? Unfortunately NO. (provable jailbreaks) Mathematically Provable Containment, Forever? YES. (sole option) Learn more: The Containment Problem (common knowledge) The AI Safety Problem (common knowledge) We do not understand how these [...]
REPORT. ASSESSING PROMPT INJECTION RISKS IN 200+ CUSTOM GPTS
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. A very good read from a respected source! REPORT. ASSESSING PROMPT INJECTION RISKS IN 200+ CUSTOM GPTS ABSTRACT In the rapidly evolving landscape of artificial intelligence, ChatGPT has [...]
MOLLY ROSE FOUNDATION REPORT. Preventable yet pervasive. The prevalence and characteristics of harmful content, including suicide and self-harm material, on Instagram, TikTok and Pinterest.
FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER. A very good read from a respected source! REPORT. Preventable yet pervasive. The prevalence and characteristics of harmful content, including suicide and self-harm material, on Instagram, TikTok and [...]