Andreas Stuhlmüller

Researcher at Ought

Wiki Contributions


2021 AI Alignment Literature Review and Charity Comparison

Ought co-founder here. Seems worth clarifying how Elicit relates to alignment (cross-posted from EA forum):

1 - Elicit informs how to train powerful AI through decomposition

Roughly speaking, there are two ways of training AI systems:

  1. End-to-end training
  2. Decomposition of tasks into human-understandable subtasks

We think decomposition may be a safer way to train powerful AI if it can scale as well as end-to-end training.

Elicit is our bet on the compositional approach. We’re testing how feasible it is to decompose large tasks like “figure out the answer to this science question by reading the literature” by breaking them into subtasks like:

  • Brainstorm subquestions that inform the overall question
  • Find the most relevant papers for a (sub-)question
  • Answer a (sub-)question given an abstract for a paper
  • Summarize answers into a single answer

Over time, more of this decomposition will be done by AI assistants.

At each point in time, we want to push the compositional approach to the limits of current language models, and keep up with (or exceed) what’s possible through end-to-end training. This requires that we overcome engineering barriers in gathering human feedback and orchestrating calls to models in a way that doesn’t depend much on current architectures.

I view this as the natural continuation of our past work where we studied decomposition using human participants. Unlike then, it’s now possible to do this work using language models, and the more applied setting has helped us a lot in reducing the gap between research assumptions and deployment.

2 - Elicit makes AI differentially useful for AI & tech policy, and other high-impact applications

In a world where AI capabilities scale rapidly, I think it’s important that these capabilities can support research aimed at guiding AI development and policy, and more generally help us figure out what’s true and make good plans as much as they help persuade and optimize goals with fast feedback or easy specification.

Ajeya mentions this point in The case for aligning narrowly superhuman models:

"Better AI situation in the run-up to superintelligence: If at each stage of ML capabilities progress we have made sure to realize models’ full potential to be helpful to us in fuzzy domains, we will be going into the next stage with maximally-capable assistants to help us navigate a potentially increasingly crazy world. We’ll be more likely to get trustworthy forecasts, policy advice, research assistance, and so on from our AI assistants. Medium-term AI challenges like supercharged fake news / clickbait or AI embezzlement seem like they would be less severe. People who are pursuing more easily-measurable goals like clicks or money seem like they would have less of an advantage over people pursuing hard-to-measure goals like scientific research (including AI alignment research itself). All this seems like it would make the world safer on the eve of transformative AI or AGI, and give humans more powerful and reliable tools for dealing with the TAI / AGI transition."

Beth mentions the more general point in Risks from AI persuasion under possible interventions: 

“Instead, try to advance applications of AI that help people understand the world, and advance the development of truthful and genuinely trustworthy AI. For example, support API customers like Ought who are working on products with these goals, and support projects inside OpenAI to improve model truthfulness.”

Competition: Amplify Rohin’s Prediction on AGI researchers & Safety Concerns

Rohin has created his posterior distribution! Key differences from his prior are at the bounds:

  • He now assigns 3% rather than 0.1% to the majority of AGI researchers already agreeing with safety concerns.
  • He now assigns 40% rather than 35% to the majority of AGI researchers agreeing with safety concerns after 2100 or never.

Overall, Rohin’s posterior is a bit more optimistic than his prior and more uncertain.

Ethan Perez’s snapshot wins the prize for the most accurate prediction of Rohin's posterior. Ethan kept a similar distribution shape while decreasing the probability >2100 less than the other submissions.

The prize for a comment that updated Rohin’s thinking goes to Jacob Pfau! This was determined by a draw with comments weighted proportionally to how much they updated Rohin’s thinking.

Thanks to everyone who participated and congratulations to the winners! Feel free to continue making comments and distributions, and sharing any feedback you have on this competition.

Ought: why it matters and ways to help

Thanks for this post, Paul!

NOTE: Response to this post has been even greater than we expected. We received more applications for experiment participant than we currently have the capacity to manage so we are temporarily taking the posting down. If you've applied and don't hear from us for a while, please excuse the delay! Thanks everyone who has expressed interest - we're hoping to get back to you and work with you soon.

Factored Cognition

What I'd do differently now:

  • I'd talk about RL instead of imitation learning when I describe the distillation step. Imitation learning is easier to explain, but ultimately you probably need RL to be competitive.
  • I'd be more careful when I talk about internal supervision. The presentation mixes up three related ideas:
    • (1) Approval-directed agents: We train an ML agent to interact with an external, human-comprehensible workspace using steps that an (augmented) expert would approve.
    • (2) Distillation: We train an ML agent to implement a function from questions to answers based on demonstrations (or incentives) provided by a large tree of experts, each of which takes a small step. The trained agent is a big neural net that only replicates the tree's input-output behavior, not individual reasoning steps. Imitating the steps directly wouldn't be possible since the tree would likely be exponentially large and so has to remain implicit.
    • (3) Transparency: When we distill, we want to verify that the behavior of the distilled agent is a faithful instantiation of the behavior demonstrated (or incentivized) by the overseer. To do this, we might use approaches to neural net interpretability.
  • I'd be more precise about what the term "factored cognition" refers to. Factored cognition refers to the research question whether (and how) complex cognitive tasks can be decomposed into relatively small, semantically meaningful pieces. This is relevant to alignment, but it's not an approach to alignment on its own. If factored cognition is possible, you'd still need a story for leveraging it to train aligned agents (such as the other ingredients of the iterated amplification program), and it's of interest outside of alignment as well (e.g. for building tools that let us delegate cognitive work to other people).
  • I'd hint at why you might not need an unreasonably large amount of curated training data for this approach to work. When human experts do decompositions, they are effectively specifying problem solving algorithms, which can then be applied to very large external data sets in order to generate subquestions and answers that the ML system can be trained on. (Additionally, we could pretrain on a different problem, e.g. natural language prediction.)
  • I'd highlight that there's a bit of a sleight of hand going on with the decomposition examples. I show relatively object-level problem decompositions (e.g. Fermi estimation), but in the long run, for scaling to problems that are far beyond what the human overseer could tackle on their own, you're effectively specifying general algorithms for learning and reasoning with concepts, which seems harder to get right.