Jack Hopkins

“The abstractions and the code structures that the model invented would align quite closely with the topology of the factory it had created.”

Expects: The speaker hoped that the model's abstractions and code structures would closely reflect the layout of the Factorio factory it built. · no date given · not yet resolved

“Let's say it had one section which was just about mining and then one section which was just about manufacturing. I was kind of hoping to see that it was able to bring that out and abstract that away to enable it to generalize better in future.”

Expects: The speaker hoped that a model would identify and abstract functional sections of a Factorio factory, such as mining and manufacturing, to improve future generalization. · no date given · not yet resolved

“In this instrumental convergence hypothesis, the paperclip maximizer hypothesis, where we think that certain behaviors are always going to emerge regardless of whether it's a human doing it or whether it's a machine,”

Expects: Certain behaviors are bound to emerge in either humans or machines, as proposed by the instrumental convergence and paperclip maximizer hypotheses. · no date given · not yet resolved

“So one thing we want to bring out in our next work is how much improvement can you get from allowing the models to take screenshots of part of the factories they want to debug.”

Expects: The team plans to test whether allowing models to screenshot factory areas for debugging improves their performance, and by how much. · no date given · not yet resolved

“basically build a paperclip maximizer and see whether this behavior emerges, because if it does, that I think might force us to change our attitude towards alignment, which is heavily based on this kind of incremental approach.”

Expects: If goal-content integrity emerges, it might require changing the prevailing attitude toward alignment, which the speaker characterizes as heavily reliant on an incremental approach. · no date given · not yet resolved

“But if we get to a point where the models are very clever and they don't want to have their objectives changed, it kind of means we only have one really good shot to set their objectives ahead of time because otherwise it's going to become quite hard to do it down the road.”

Expects: If models become very capable and resist having their objectives changed, the speaker believes there may be only one good opportunity to set their objectives beforehand, because changing them later will become difficult. · no date given · not yet resolved

“which the models can kind of choose to configure when they invoke it as a tool and the hope there is that we can stumble upon stumble upon the right vision mode that these models are reasonably good at but by i think your intuition is right i would be surprised if we get that much from it at this stage but it would be it would be cool if we do”

Expects: The team hopes to find a vision mode that models can use reasonably well, though the speaker expects little improvement from vision at the current stage. · no date given · not yet resolved

“this gives agents a lot of reach as the factories get bigger you can imagine they could create you know quite sophisticated like for example they could create hypothetically an NSAT solver in the kind of name space and then use that for a correct item and entity positioning in the game if they were able to do this”

Expects: As Factorio factories grow, agents might create sophisticated tools, such as an NSAT solver, and use them to position items and entities correctly in the game. · no date given · not yet resolved

“it may not be directly applicable to the agent's immediate objective it didn't really give us any uptick in scores so i think we kind of put that in the bucket of what we're going to do when we when we start really throwing computer so for example we when we did all these experiments we kind of accumulated about a million programs that agents have written with scores attached so we kind of got this big bucket of programs and traces trajectories through the game and we want to take these and just kind of throw it at a model and just and just see what happens if we really try and get it to learn how to maximize score directly,”

Expects: The team will train a model on its collected Factorio programs and trajectories to test whether it can learn to maximize the game score directly. · no date given · not yet resolved

“put them in the game and then compare it with the models because the models you know they have never been trained on this stuff they only know a little bit about factorio they they have the manual of how to interact with it and they just they just have to go and and try their best so maybe that's what we should do i should try and recruit my fiance and kind of make her sit down for for 10 hours in front of the game and see where we get”

Expects: The speaker might recruit his fiancée to play Factorio for 10 hours as part of a comparison with the models. · no date given · not yet resolved