Aligned AI is an Oxford based startup focused on applied alignment research. Our goal is to implement scalable solutions to the alignment problem, and distribute these solutions to actors developing powerful transformative artificial intelligence (related Alignment Forum post here).
In the tradition of AI safety startups, Aligned AI will be doing an AMA this week, from today, Tuesday the 1st of March, till Friday the 4th, inclusive. It will be mainly me, Stuart Armstrong, answering these questions, though Rebecca Gorman and Oliver Daniels-Koch may also answer some of them. GPT-3 will not be invited.
From our post introducing Aligned AI:
We think AI poses an existential risk to humanity, and that reducing the chance of this risk is one of the most impactful things we can do with our lives. Here we focus not on the premises behind that claim, but rather on why we're particularly excited about Aligned AI's approach to reducing AI existential risk.
- We believe AI Safety research is bottle-necked by a core problem: how to extrapolate values from one context to another.
- We believe solving value extrapolation is necessary and almost sufficient for alignment.
- Value extrapolation research is neglected, both in the mainstream AI community and the AI safety community. Note that there is a lot of overlap between value extrapolation and many fields of research (e.g. out of distribution detection, robustness, transfer learning, multi-objective reinforcement learning, active reward learning, reward modelling...) which provide useful research resources. However, we've found that we've had to generate our most of the key concepts ourselves.
- We believe value extrapolation research is tractable (and we've had success generating the key concepts).
- We believe distributing (not just creating) alignment solutions is critical for aligning powerful AIs.
Hey :)
Disclaimer: I am no AI alignment expert, so consider skipping this comment and reading the quality ones instead. But there are no other comments yet so here goes:
If I understood correctly,
It seems to me (not that I know anything!!) like the model might update in very bad-for-humans ways, even while being well "aligned" to the initial data, and to all iterations, regardless of how they're performed.
TL;DR: I think so because concept space is superexponential and because value is fragile.
Imagine we are very stupid humans [0], and we give the AI some training data from an empty room containing a chess board, and we tell the AI which rooms-with-chess-boards are better for us. And the AI learns this well and everyone is happy (except for the previous chess world champion).
And then we run the AI and it goes outside the room and sees things very different from its training data.
Even if the AI notices the difference and alerts the humans,
And then the AI proceeds to act on models far beyond what it was trained on, and so regardless of how it extrapolated, that was an impossible task to begin with, and it probably destroys the world.
What am I missing?
[0]
Why did I use the toy empty-room-with-chess story?
Because part of the problem that I am trying to point out is "imagine how a training dataset can go wrong", but it will never go wrong if for every missing-thing-in-the-dataset that we can imagine, we automatically imagine that the dataset contains that thing.
Thanks!
So ok, the AI knows that some human values are unknown to the AI.
What does the AI do about this?
The AI can do some action that maximizes the known-human-values, and risk hurting others.
The AI can do nothing and wait until it knows more (wait how long? There could always be missing values).
Something I'm not sure I understood from the article:
Does the AI assume that the AI is able to list all the possible values that humans maybe care about? Is this how the AI is supposed to guard against any of the possible-human-values from going down too much?