On Wed, Jan 24, 2024 at 8:08 PM Nanograte Knowledge Technologies < nano...@live.com> wrote:
> Mike > > What yo might be searching for is, what I would refer to, as 'ambiguity > management'. It's still machine reasoning though, as algorithmic logic. I > think it's vital to separate this area of reasoning from 'prediction > management'. > > Most learning models take the approach that a semantic engine could > resolve and manage ambiguity. As experience would teach, it cannot do so on > its own. As a consequence, a lexicon and taxonomical (a tables nightmare) > can result. Lookup tables for AGI? Go figure! > > For AGI, one has to step away from the notion of clever apps and think > holistically in terms of seamlessly-integrated platform design. > Effectively, one is designing a universe. *In other words, in the least, > a part of the "brain-to-be" would perform semantic functionality, while > another feature would manage decision making.* > Robert, You mention "another component" and I've long thought there should be a discrete oracle component in an AGI. The Oracle would be where the bucks stops in decision making. Contemporary models like LLMs have no such separate component. It's all just output! > > > A specialized area would probably be termed 'judgment management'. Both > these areas of expertise should theoretically fall into a class called > 'ambiguity management'. > > If you revisited the, now-ancient publication, of my abstract-reasoning > method on researchgate, you'll find mention of ambiguity. In physics terms, > we may as well have called that: 'relativity management'. It's a great, but > scientifically-intensive research area. > > Enjoy your quest > > Robert > ------------------------------ > *From:* Mike Archbold <jazzbo...@gmail.com> > *Sent:* Thursday, 25 January 2024 04:31 > *To:* AGI <agi@agi.topicbox.com> > *Subject:* Re: [agi] The future of AGI judgments > > I suppose what I am looking for is really in that space beyond the > benchmark tests, in which clearly more than one decision is arguably valid > within acceptable boundaries. How does the machine gauge what such > acceptable boundaries are? What does the machine judge in cases with a > scarcity of evidence in multiple dimensions? > > Most of the emphasis on large model testing is on "understanding and > reasoning" (two words appear repeatedly in papers) but not really judging. > Judging is what we do about the output of the AI. But ultimately we want > the machine to really judge within acceptable boundaries given a scarcity > of objective evidence. Now the models usually output something like "I am > not comfortable answering that" or "I am so and so model but don't do that" > or such. Some of this comes down to intuition and gut feel in humans -- > that is, when faced with a novel situation. > > On Wed, Jan 24, 2024 at 1:31 PM Mike Archbold <jazzbo...@gmail.com> wrote: > > James, > > Thanks for the lead. I know the general nature of AIXI but haven't read > the paper. Basically what you are arguing, I think, is that everything done > by a machine is a judgment, since ultimately it's only subjective. So, we > cannot readily distinguish "fact" from "judgment" in a machine, and the > point is argued by Brian Smith in "The Promise of AI Reckoning and > Judgment." > > But the climate of opinion and practical nature of modern AI is in meeting > benchmarks in test, so there is some objectivity anyway, like it or not... > the benchmark tests are more or less inescapably "objective" I think. > > On Tue, Jan 23, 2024 at 2:55 PM James Bowery <jabow...@gmail.com> wrote: > > There are two senses in which "subjective" applies to AGI, and one must > very carefully distinguish between them or you'll end up in the weeds: > > 1) One's observations (measurement instruments) are inescapably > "localized" within the universe hence are, in that sense, "subjective". > See Hutter's paper "A *Complete* Theory of Everything (will be > subjective)". But note that one may nevertheless speak of the "ToE" which > one constructs from one's "subjective" experiences, as an "objective" > theory in the sense that one may shift one's perspective and measurement > instruments without losing what one might think of as the canonical > knowledge about the world aka "world model" that is abstracted from such > localization parameters. > > 2) One's "judgements" as you call them, or "decisions" as AIXI calls them > via Sequential *Decision* Theory, are inescapably subjective in a the > vernacular sense of "subjective" where one places *values* on one's > experiences via the *utility function* that parameterizes SDT. > > If you're going to depart from AIXI or elaborate it in some way, then it > is important to understand where, in its very concise formalization, one is > performing one's amputation and/or enhancement. > > > On Tue, Jan 23, 2024 at 3:55 PM Mike Archbold <jazzbo...@gmail.com> wrote: > > Hey everybody, I've been doing some research on the topic of judgments in > AI. Looking for some leads on where the art/science of decision making is > heading in AI/AGI. Note: by "judgment" I mean situations which have a > decision that is open to values within boundaries, not that can be > immediately and objectively correct or incorrect. > > Lately I have been studying LLM-as-a-Judge theory. I might do a survey or > such, not sure... looking for leads, comments etc. > > Thanks Mike Archbold > > *Artificial General Intelligence List <https://agi.topicbox.com/latest>* > / AGI / see discussions <https://agi.topicbox.com/groups/agi> + > participants <https://agi.topicbox.com/groups/agi/members> + > delivery options <https://agi.topicbox.com/groups/agi/subscription> > Permalink > <https://agi.topicbox.com/groups/agi/T5edfab21647324f7-M8cb764242169736077df46bc> > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T5edfab21647324f7-M9377796b5fbf6012d1b6ded2 Delivery options: https://agi.topicbox.com/groups/agi/subscription
