Just posted the following on Medium. Interested in comments from readers here, especially pointers to similar efforts and ideas I didn't mention below. This is the first in a series of articles describing features, functions, and components of Personal Agents — next generation AI virtual assistants that will serve as...
This post is to make the subject case more available and open to comment. A paper with the above title is currently languishing in arXiv limbo but available in Google Docs. I was surprised to see my last and only postings to LessWrong were made on this very subject in...
Just posted the following on Medium. Interested in comments from readers here, especially pointers to similar efforts and ideas I didn't mention below.
This is the first in a series of articles describing features, functions, and components of Personal Agents — next generation AI virtual assistants that will serve as trusted advisors, caretakers, and user proxies. Personal Agents will preferably be developed as an open source project. Primary goals are to specify agents that (1) Significantly benefit people (are not just cool or fun) and (2) Avoid harmful side-effects (like those plaguing social media or that worry AI safety advocates). A clear and open specification will facilitate agent development and certification. This article... (read 558 more words →)
I think claiming the above is a "radical solution to all problems related to the Intelligence Curse" is an overstatement. The three treaty elements you mention could be useful as part of AI-human social contracts--thus getting at a part of the Averting (i.e, AI Safety) piece . But many more treaty elements (Laws, Rules) are also needed IMO.
The Diffusing and Democratizing (and maybe other) pieces are also needed for an effective solution.
(Also, unclear what you mean by "obeying all orders except the ones determined by the Spec." What Spec?)
Really enjoyed your essay series. Appreciated it offered a positive future vision and then a roadmap for how to get there. Both are important. Too many people seem to be sleepwalking into a sketchy AGI future.
Here's my vision from a 2022 Future of Life Institute contest: "A future where sentient beings thrive due to widespread agreement on core values; improvements in education; Personal Agent AIs; social simulations; and updated legal systems (based on the core values) that are fair, nimble, and capable of controlling dangerous humans and AGIs. Of the core values, Truth and Civility are particularly impactful in keeping the world moving in a positive direction." Full scenario here.
Compare with yours:
... (read more)We
Yup!
Fixed link: https://medium.com/@jeffj4a/personal-agents-will-enable-direct-democracy-9413f5607c15
I developed this idea here: https://medium.com/@jeffj4a/personal-agents-will-enable-direct-democracy-9413f5607c15 Pretty much the same byline as yours. :-)
[Fixed link]
Sure. Getting appropriate new laws enacted is an important element. From the paper:
Initially, in addition to adopting existing bodies of law to implement AISVL, existing processes for how laws are drafted, enacted, enforced, litigated, and maintained would be preserved.
Thereafter, new laws and improvements to existing laws and processes must continually be introduced to make the systems more robust, fair, nimble, efficient, consistent, understandable, accepted, complied with, and enforced.
I'd say the EU AI Act (and similar) work addresses the "new laws" imperative. (I won't comment (much) on pros and cons of its content. In general, it seems pretty good. I wonder if they considered adding Etzioni's first law to the mix, "An AI... (read more)
If an AI can be Aligned externally, then it's already safe enough. It feels like...
- You're not talking about solving Alignment, but talking about some different problem. And I'm not sure what that problem is.
- For your proposal to work, the problem needs to be already solved. All the hard/interesting parts need to be already solved.
I'm talking about the need for all AIs (and humans) to be bound by legal systems that include key consensus laws/ethics/values. It may seem obvious, but I think this position is under-appreciated and not universally accepted.
By focusing on the external legal system, many key problems associated with alignment (as recited in the Summary of Argument) are addressed. One worth highlighting is 4.4, which suggests AISVL can assure alignment in perpetuity despite changes in values, environmental conditions, and technologies, i.e., a practical implementation of Yudkowsky's CEV.
I'm not sure exactly how many people are working on it, but I have the impression that it is more than a dozen, since I've met some of them without trying.
Glad to hear it. I hope to find and follow such work. The people I'm aware of are listed on pp. 3-5 of the paper. Was happy to see O'Keefe, Bai et al. (Anthropic), and Nay leaning this way.
... (read more)It seems to me like you are somewhat shrugging off those concerns, since the technological interventions (eg smart contracts, LLMs understanding laws, whatever self-driving-car people get up to) are very "light" in the face of those "heavy" concerns. But a legal approach need not
I believe you have to argue two things:
- Laws are distinct enough from human values (1), but following laws / caring about laws / reporting about predicted law violations prevents the violation of human values (2).
I think the post fails to argue both points. I see no argument that instilling laws is distinct enough from instilling values/corrigibility/human semantics in general (1) and that laws actually prevent misalignment (2).
My argument goes in a different direction. I reject premise (1) and claim there is an "essential equivalence and intimate link between consensus ethics and democratic law [that] provide a philosophical and practical basis for legal systems that marry values and norms (“virtue cores”) with rules... (read more)
I feel as if there is some unstated idea here that I am not quite inferring. What is the safety approach supposed to be? If there were an organization devoted to this path to AI safety, what activities would that organization be engaged in?
The summary I posted here was just a teaser to the full paper (linked in pgph. 1). That said, your comments show you reasoned pretty closely to points I tried to make therein. Almost no need to read it. :)
... (read 450 more words →)The first part is just "regulation". The second part, "instilling law-abiding values in AIs and humans", seems like a significant departure. It seems like the proposal involves both (a) designing
This post is to make the subject case more available and open to comment. A paper with the above title is currently languishing in arXiv limbo but available in Google Docs. I was surprised to see my last and only postings to LessWrong were made on this very subject in 2010 as comments to the thread "Why not just write failsafe rules into the superintelligent machine?"
Unfortunately (IMO) this approach to AI alignment doesn't seem to have gained much traction in the past 13 years. The paper does cite, however, 15 precedents that show there is some support. (Anthropic's Constitutional AI and John Nay's Law Informs Code are two good recent examples.)
The following... (read 1046 more words →)