Headline, October 09 2024/ ''' AN -INDUSTRIAL WORLD- AI '''

''' AN -INDUSTRIAL

 WORLD- AI '''

BREAKING - MAKING : '' REASONS TO BE FEARFUL.'' Expected overall impact of advanced AI on humanity. Even GPT-4 which has been extensively red-teamed, is not infallible.

So called ''jailbreakers'' have put together websites littered with techniques for getting around the model's guardrails, such as by telling the model that it is role-playing in a fictional world.

Sam Bowman of New York University and also of Anthropic, an AI firm, thinks that pre-launch screening '' is going to get harder as systems get better ''. Another risk is that AI models learn to game the tests, said Holden Karnofsky, an adviser to ARC and former board member of OpenAI.

Just as people '' being supervised to learn the patterns ..... they learn to know when someone is trying to trick them''. At some point AI systems might do that, he thinks.

Another idea is to use AI to police AI. Dr. Bowman has written papers on techniques like '' Constitutional AI '', in which a secondary AI model is asked to assess whether output from the main model adheres to certain '' constitutional principles''.

Those critiques are then used to fine-tune the main model. One attraction is that it does not need human labellers.

And, computers tend to work faster than people, so a constitutional system might catch more problems than one tuned by humans alone -though it leaves open the question of who writes the constitution.

Some researchers, including Dr Bowman, think that what ultimately may be necessary is what AI researchers call '' interpretability '' - a deep understanding of how exactly models produce their outputs.

One of the problems with machine-learning models is that they are '' black boxes ''. A conventional program is designed in a human's head before being committed to code. In principle, at least, that designer can explain what the machine is supposed to be doing.

But machine-learning models program themselves. What they come up with is often incomprehensible to humans.

Progress has been made on very small models using techniques like '' mechanistic interpretability ''.

This involves reverse engineering AI models, or trying to map individual parts of a model to a specific patterns in its training data, a bit like neuro-scientists prodding living brains to work out which bits seem to be involved in vision, say, or memory. The problem is this method becomes exponentially harder with bigger models.

The lack of progress on interpretability is one reason why many researchers say that the field needs regulation to prevent ''extreme scenarios ''. But the logic of commerce pulls in the opposite direction :

Microsoft just last year, fired its AI ethics team, for example. Indeed, some researchers think the true '' alignment '' problem is that AI firms, like polluting factories, are not aligned with the aims of society.

They financially benefit from powerful models but do not internalise the costs borne by the world of releasing them prematurely.

Even if efforts to produce '' safe '' models work, future open-source versions could get around them. Bad actors could fine-tune models to be unsafe, and then release them publicly.

For example AI models have already made new discoveries in biology. It is not inconceivable that they one day design dangerous biochemicals.

The most extreme risks, in which AIS become so clever as to outwit humanity, seems to require an '' intelligence explosion '', in which an AI works out how to make itself cleverer.

The Honour and Serving of the Latest Global Operational Research on AI, Researchers and the Future Models, continues. The World Students Society thanks The Economist.

With respectful dedication to the Global Founder Framers of The World Students Society - the exclusive and eternal ownership of every student in the world - and then Students, Professors and Teachers.

See You all prepare for Great Global Elections on !WOW! - for every subject in the world - : wssciw.blogspot.com and Twitter X !E-WOW! - The Ecosystem 2011 :

Good Night and God Bless

SAM Daily Times - the Voice of the Voiceless