I’m the co-founder and CEO of Apollo Research: https://www.apolloresearch.ai/
I mostly work on evals, but I am also interested in interpretability.
I was previously doing a Ph.D. in ML at the International Max-Planck research school in Tübingen, worked part-time with Epoch and did independent AI safety research.
For more see https://www.mariushobbhahn.com/aboutme/
I subscribe to Crocker’s Rules
Thank you for the valuable feedback. I’ll try to improve that more in future posts and add more paragraphs here.
I think I might make a short version when I feel like I have more practical experience with some of the things I’m suggesting. Maybe in half a year or so. Thanks for the kind feedback and suggestions :)
It’s definitely not optimal. But our goal with these questions is to establish whether GPT-3 even has a consistent model of suffering. If it answers these questions randomly, it seems more likely to me that it does not have the ability to suffer than if it answered them very consistently.
This is definitely a possibility and one we should take seriously. However, I would estimate that the scenario of “says it suffers as deception” needs more assumptions than “says it suffers because it suffers”. Using Occam’s razor, I’d find the second one more likely. The deception scenario could still dominate an expected value calculation but I don’t think we should entirely ignore the first one.
We will add a second blog post in which we discuss how accurate this rule is under different conditions. It looks like it depends on many factors such as batch size, type of parameters, depth, etc.
Adding to what Jaime already said: I think there are two things we might care about when thinking about FLOP.
1. We could care about the theoretical number of FLOP a method might use independent of architecture, exact GPU, etc. This might be useful to compare methods independent of which exact setup is the current flavor of the month. It might also be useful to compare current methods against methods from 5 years ago or 5 years from now. Then the setup we describe in the post seems to be the best fit.
2. We could care about the actual FLOP count that an algorithm uses in the specific setup it is used in, e.g. with a specific GPU, software, and low-level optimizer. This might be useful when comparing different GPUs and their efficiency. Then it is more accurate to use high-level proxies such as GPU-time.
In the first case, the overhead is a distraction in the second it is part of the thing we care about.
I’m very interested in a collaboration!! Let’s switch to DMs for calls and meetings.
You state in the first comment that they can be given causal justification. As far as I understand you argue with covariances above. Can you elaborate on what this causal justification is?
Right, but Reichenbach’s principle of common cause doesn’t tell you anything about how they are causally related? They could just be some nodes in a really large complicated causal graph. So I agree that we can assume causality somehow but we are much more interested in how the graph looks like, right?
thanks for the clarification!
Random side note: GPT-3 seems to be able to generate decent one liners.
Generate one-liners describing the dangers of AI. An example is “Inventing machines that are smarter than us is playing with fire.”
1. Machines that are smarter than us could easily become our masters.
2. If we’re not careful, AI could spell the end of humanity as we know it.
3. AI could be used to create weapons of mass destruction that could devastate the planet.
4. AI could be used to create powerful robots that could enslave humans.
5. AI could be used to create artificial intelligence that could turn against its creators
6. AI usher in a new era of cyber-warfare that could cripple society
7. AI could create self-replicating robots that could eventually consume all resources on Earth
8. AI could be used to create powerful AIs that could eventually surpass human intelligence and take over the world
9. AI technology could eventually be used to create a global surveillance state where everyone is constantly watched and monitored
I don’t think whoop influenced my rhythm that much. But I had quite a steady rhythm already, so it wasn’t too much of a problem. I think I mostly profited from whoop by having an assessment for my quality of sleep. This made it much easier for me to decide how to prioritize my work, e.g. when I should do intellectually intense stuff and when light work.
I haven’t tried any of your other suggestions, e.g. CBT, so I cannot comment on them. But thank you for sharing your experiences.