An Open Letter to HALT Giant A.I. Experiments is No Big Request. It’s a MONSTROUS REQUEST! And suddenly, has Man finally realized that A.I. is getting so Big so Rapidly, that A.I. could, in the right hands, Shutdown the Entire World? Shutdown Railroads, Airplanes, Cars, Trucks, Entire Industries overnight. Suddenly put the World in the Dark. Completely shuts the World Down. Shuts down all Satellites. Give Dark Countries complete Control of the World? But in the Hands of a Dictator? Your Freedoms stolen without a shot being Fired? Oh My!
The possibilities are now suddenly being realized. And the Researchers aren’t sure what other Researchers are doing? But TOTAL CONTROL is the End Game all are after. Isn’t it?
And exactly what is the GPT-4 Level that they wanted halted for 6 months?
As an AI language model, GPT-4 is expected to be even more advanced than its predecessor GPT-3. It could have the ability to generate more human-like text, understand and respond to increasingly complex natural language queries, and potentially have the capability to reason and analyze data in more sophisticated ways. It could also have improvements in machine translation, text summarization, and text completion tasks. However, it is important to note that GPT-4 has not been officially announced or released yet, so these are just predictions based on the existing trend of improvement in language models. As an AI language model, it is likely that GPT-4 will focus primarily on developing its natural language generation capabilities. However, it is also possible that GPT-4 may be designed to incorporate other features and capabilities beyond natural language processing. For example, it could potentially be programmed to perform other tasks such as image recognition, voice recognition, or even advanced reasoning and decision-making capabilities. Ultimately, the specific capabilities of GPT-4 will depend on the goals and priorities of its developers.
As an AI language model, I am not privy to any information about forthcoming products or their intended uses. However, in general, a GPT-4 model for military applications could be used for a variety of purposes. One potential use could be for natural language processing and analysis of large datasets, such as intelligence reports or satellite imagery. This could enable military planners to make more informed decisions based on real-time data analysis. Additionally, a GPT-4 model could be used to aid in the development of strategic plans or to assist with language translation for communications with foreign allies or adversaries. Ultimately, the specific application of a GPT-4 model within a military context would be determined by the needs of the military organization in question. It is possible that a GPT-4 AI could be used in the financial industry in the future. GPT-4, being a natural language processing AI, has the ability to analyze large amounts of text data and extract insights from them. In the financial industry, this could be useful for tasks such as analyzing market sentiment, identifying patterns and trends in financial data, and even providing investment recommendations based on the analyzed data. However, ethical concerns about the potential biases of machine learning algorithms and the reliability of their outputs would need to be addressed before they can be incorporated in any decision-making processes.
Below is a 100-page PDF to explain gpt-4 to everyone. The 1st two pages are screenshots
Fearing “loss of control,” AI critics call for 6-month pause in AI development
Pause Giant AI Experiments: An Open Letter
We call on all AI labs to immediately pause for at least 6 months the training of AI systems more powerful than GPT-4.
AI systems with human-competitive intelligence can pose profound risks to society and humanity, as shown by extensive research[1] and acknowledged by top AI labs.[2] As stated in the widely-endorsed Asilomar AI Principles, Advanced AI could represent a profound change in the history of life on Earth, and should be planned for and managed with commensurate care and resources. Unfortunately, this level of planning and management is not happening, even though recent months have seen AI labs locked in an out-of-control race to develop and deploy ever more powerful digital minds that no one – not even their creators – can understand, predict, or reliably control.
Contemporary AI systems are now becoming human-competitive at general tasks,[3] and we must ask ourselves: Should we let machines flood our information channels with propaganda and untruth? Should we automate away all the jobs, including the fulfilling ones? Should we develop nonhuman minds that might eventually outnumber, outsmart, obsolete and replace us? Should we risk loss of control of our civilization? Such decisions must not be delegated to unelected tech leaders. Powerful AI systems should be developed only once we are confident that their effects will be positive and their risks will be manageable. This confidence must be well justified and increase with the magnitude of a system’s potential effects. OpenAI’s recent statement regarding artificial general intelligence, states that “At some point, it may be important to get independent review before starting to train future systems, and for the most advanced efforts to agree to limit the rate of growth of compute used for creating new models.” We agree. That point is now.
Therefore, we call on all AI labs to immediately pause for at least 6 months the training of AI systems more powerful than GPT-4. This pause should be public and verifiable, and include all key actors. If such a pause cannot be enacted quickly, governments should step in and institute a moratorium.
AI labs and independent experts should use this pause to jointly develop and implement a set of shared safety protocols for advanced AI design and development that are rigorously audited and overseen by independent outside experts. These protocols should ensure that systems adhering to them are safe beyond a reasonable doubt.[4] This does not mean a pause on AI development in general, merely a stepping back from the dangerous race to ever-larger unpredictable black-box models with emergent capabilities.
AI research and development should be refocused on making today’s powerful, state-of-the-art systems more accurate, safe, interpretable, transparent, robust, aligned, trustworthy, and loyal.
In parallel, AI developers must work with policymakers to dramatically accelerate development of robust AI governance systems. These should at a minimum include: new and capable regulatory authorities dedicated to AI; oversight and tracking of highly capable AI systems and large pools of computational capability; provenance and watermarking systems to help distinguish real from synthetic and to track model leaks; a robust auditing and certification ecosystem; liability for AI-caused harm; robust public funding for technical AI safety research; and well-resourced institutions for coping with the dramatic economic and political disruptions (especially to democracy) that AI will cause.
Humanity can enjoy a flourishing future with AI. Having succeeded in creating powerful AI systems, we can now enjoy an “AI summer” in which we reap the rewards, engineer these systems for the clear benefit of all, and give society a chance to adapt. Society has hit pause on other technologies with potentially catastrophic effects on society.[5] We can do so here. Let’s enjoy a long AI summer, not rush unprepared into a fall.
SUDDENLY!
Has everyone realized that any groups of Researchers could take an Advanced A.I. where man only thought it was possible. Has man now realized how quickly TERMINATOR could be realized in an ClosedA.I. Or better put, Top Secret applications where man will take control of the World?
thelivingbreathingjamesbrown.com 
You must be logged in to post a comment.