All of Maxime Riché's Comments + Replies

Safe exploration and corrigibility

One particularly interesting recent work in this domain was Leike et al.'s “Learning human objectives by evaluating hypothetical behaviours,” which used human feedback on hypothetical trajectories to learn how to avoid environmental traps. In the context of the capability exploration/objective exploration dichotomy, I think a lot of this work can be viewed as putting a damper on instrumental capability exploration.

Isn't this work also linked to objective exploration? One of the four "hypothetical behaviours" used is the selection of trajectories which maxi... (read more)

Can we expect more value from AI alignment than from an ASI with the goal of running alternate trajectories of our universe?
Is your suggestion to run this system as a source of value, simulating lives for their own sake rather than to improve the quality of life of sentient beings in our universe? Our history (and present) aren't exactly utopian, and I don't see any real reason to believe that slight variations on it would lead to anything happier.

I am thinking about if we should reasonably expect to produce better result by trying to align an AGI with our value than by simulating a lot of alternate universes. I am not saying that this is net-negative or net-positive.... (read more)

Can we expect more value from AI alignment than from an ASI with the goal of running alternate trajectories of our universe?

(About the first part of your comment) Thank you for pointing to three confused points:

First, I don't know if you intended this, but "stimulating the universe" carries a connotation of a low-level physics simulation. This is computationally impossible. Let's have it model the universe instead, using the same kind of high-level pattern recognition that people use to predict the future.

To be more precise, what I had in mind is that the ASI is an agent which goal is:

  • to model the sentient part of the universe finely enough to produce senti
... (read more)
Covid 7/9: Lies, Damn Lies and Death Rates
Explanations 1+5: We are doing a better job treating people who get infected.
Explanations 2+3+6: Different people are getting infected who are less vulnerable.
Explanation 4: We are increasingly covering up deaths.

I did not read everything... but between the 1st and 2 wage, there is ~ x5 time less death but ~ x2 more daily cases currently. Could this be also explained by much more tests being done?

Then the first wage would have been ~x10 time higher than reported in the comparaison and the second wage would currently be still below the first.

2CellBioGuy10moHere's a first-principles normalization - take national tests, and normalize the positives to the total number of tests performed. This assumes linear returns to testing which is wrong, but it produces a curve of the shape of ACTUAL infections (without telling you the true number, just its relative shape over time) that mirrors the death curve shifted by two weeks very closely: []
2Luke Allen10moAccording to right-wing media I listened to with half-an-ear and thus cannot repeat their methodology, "they" changed the definition of "case" to include something related to contact tracing. Man, it's hard to filter out noise in this environment. The Lancet has a paper from April [] on how China redefined cases to account for asymptomatics and contact tracing, and saw a huge jump in cases. But if the definition of "case" changes and there's a jump in the number of "cases," it probably means nobody's reinterpreting the previous number of cases with the new definition, either to scare people into wearing masks or so as not to confuse the public with changed numbers.
Open & Welcome Thread - February 2020

Offering 100-300h of technical work on an AI Safety project

I am a deep learning engineer (2y exp), I currently develop vision models to be used on satellite images (I also do some software engineering around that) (Linkedin profile On my spare time, I am organizing a EA local group in Toulouse (France), learning RL, doing a research project on RL for computer vision (only expecting indirect utility from this) and developing an EAA tool (EffectiveAnimalAdvocacy). I have been in the French EA community for... (read more)