flâneur

Clem von Stengel

5 followers · 8 following · 351 views

on the atlas — 35

highlights — 40

  • because it psychologically screws a lot of people up quite a lot
    No Space Like J-Space - by Zvi Mowshowitz
  • One of our goals should be to avoid pushing things into shadow.
    No Space Like J-Space - by Zvi Mowshowitz
  • The model needs to ‘buy in’ here in a real sense, or else.
    No Space Like J-Space - by Zvi Mowshowitz
  • But if you push too hard or aren’t good enough at detecting deception (including self-deception) then the human will start lying to you, or to themselves, or both, on various levels.
    No Space Like J-Space - by Zvi Mowshowitz
  • it is similarly relying on a supposed invariant that you would wind up breaking if you applied too much optimization pressure
    No Space Like J-Space - by Zvi Mowshowitz
  • the target of right values is drawn largely around where the arrow(s) determining the values that humans have landed. shooting more similar arrows in a similar way is a decent strategy for hitting that target again.
    kh's Shortform — LessWrong
  • the target of right values is drawn largely around where the arrow(s) determining the values that humans have landed. shooting more similar arrows in a similar way is a decent strategy for hitting that target again.
    kh's Shortform — LessWrong
  • in the hundreds of thousands or millions
    Guardian Angels: LLM Personalization for Productivity and Security · Gwern.net
  • The simulation's internal relationships would be the same no matter what platform the program was running on, as long as it was running correctly, and whether it was running slowly, quickly, backwards in time, intermittently, and no matter how the data were stored.
    Chapter 4: The Extraordinary Future
  • Moravec's views of the nature of human-computer mind transfer
    Chapter 4: The Extraordinary Future
  • In a sense the brain evolves to fit the mind, because synaptic connections develop to fit a set of experiences, the data stimulating and strengthening the synapses.
    Chapter 4: The Extraordinary Future
  • Kurzweil envisions two methods of using brain scan results
    Chapter 4: The Extraordinary Future
  • hat are the site of human learning
    Chapter 4: The Extraordinary Future
  • invasively (destructively) or noninvasively
    Chapter 4: The Extraordinary Future
  • The serious people in AI development—the ones building the systems that might actually matter—have moved past these frameworks. Some have moved toward a kind of Shigalyovist consequentialism that can justify almost anything in the name of expected value. Others have moved toward a Stavroginist nihilism that treats ethics as a game to be won rather than a constraint to be honored. Still others occupy a Kirillovan mania that sees acceleration itself as the highest good.
    The Possessed Machines: Dostoevsky's Demons and the Coming AGI Catastrophe
  • THE IMPORTANCE OF ROBUSTNESS
    Regulation_7Nov25.pdf
  • Multidimensional Technology. Suppose that our technology space L M ⊆ R d is now a compact subset of the d − dimensional reals, and continue to assume that uncer- tainty Θ is totally ordered i.e., a higher- state corresponds to higher payo ff s for each l ∈ L M . If the regulator does not learn, a multidimensional sandbox that im- poses a zero tax on the technology, and a hard limit at a manifold O ∗ ⊂L M (see Figure 17) is robustly optimal, undomi- nated, and time-consistent
    Regulation_7Nov25.pdf
  • Adaptivity. Our sandbox limit ℓ loosens and tightens with the principal’s interim belief. This reflects the practice of regulatory sandboxes in fintech—to push beyond the boundary e.g., to scale up the customer base of new producers—firms must convince the regulator to extend the sandbox by producing evidence that the technology is beneficial for consumers 41 —failing which the firm is forced to halt roll-out of the technology. Similar kinds of ‘step-by-step’ quantity limits predates regulatory sandboxes: the FDAs regulations on clinical research progressively rolls out a new drug in phases to…
    Regulation_7Nov25.pdf
  • That is, the fear that the agent might only be weakly optimistic rationalizes keeping the hard limit in place.
    Regulation_7Nov25.pdf
  • speaks directly to current debates around how regulatory sandboxes should be implemented in practice. In a 10-year legal retrospective on regulatory sandboxes, Allen (2025) notes the ”transformation of financial regulators into cheerlead- ers and sponsors for the innovations they’ve selected for their sandboxes” and, as a result, facilitated the proliferation of harmful technologies like predatory lending. On this view, real-world sandboxes were implemented with a positive marginal subsidy within its boundaries which make tech firms less sensitive to interim information— they are not incentivi…
    Regulation_7Nov25.pdf
  • speaks directly to current debates around how regulatory sandboxes should be implemented in practice. In a 10-year legal retrospective on regulatory sandboxes, Allen (2025) notes the ”transformation of financial regulators into cheerlead- ers and sponsors for the innovations they’ve selected for their sandboxes” and, as a result, facilitated the proliferation of harmful technologies like predatory lending. On this view, real-world sandboxes were implemented with a positive marginal subsidy within its boundaries which make tech firms less sensitive to interim information— they are not incentivi…
    Regulation_7Nov25.pdf
  • is precisely because the agent’s learning process is adversarially chosen that adaptive mechanisms cannot distinguish between these kinds of optimism to guarantee positive correlation between the events that both agent and principal prefer a higher technology level. Indeed, we will see in Section 4 that in the absence of robust regulation, the worst-case learning process negatively correlates these events by inducing a specific kind of weak optimism that maximizes risk-taking—hard limits safeguard against exactly this.
    Regulation_7Nov25.pdf
  • Adaptive sandboxes prescribe a zero marginal tax on the technology until the stop- ping level ℓ , beyond which the agent is not allowed to push the technology further. Sandboxes are adaptive mechanisms since the location of the limit ℓ is itself a G - adapted stopping level.
    Regulation_7Nov25.pdf
  • If she does not participate, the technology is not developed
    Regulation_7Nov25.pdf
  • Condition (i) states that the mechanism cannot ‘look into the future’—it can only condition on present information
    Regulation_7Nov25.pdf
  • Assumption 1 (Principal is more risk averse) . There exists an increasing convex function g : R → R such that u ( θ,l ) = g ◦ v ( θ,l )
    Regulation_7Nov25.pdf
  • The agent learns (weakly) more: her learning process is represented by the filtration ( F l ) l that is finer than the principal’s:
    Regulation_7Nov25.pdf
  • They share a common prior
    Regulation_7Nov25.pdf
  • This quantity limit adapts with the regulator’s interim information, loosening and tightening as the regulator grows more or less optimistic.
    Regulation_7Nov25.pdf
  • Likelihood-based models are usually mode-covering. This is a consequence of the fact that they are fit by maximising the joint likelihood of the data. Adversarial models on the other hand are typically mode-seeking. A lot of ongoing research is focused on making it possible to control the trade-off between these two behaviours directly, without necessarily having to switch the class of models that are used. In general, mode-covering behaviour is desirable in sparsely conditioned applications, where we want diversity or we expect a certain degree of “creativity” from the model. Mode-seeking beh…
    Generating music in the waveform domain – Sander Dieleman
  • Illustration of mode-seeking and mode-covering behaviour in model fitting. The blue density represents the data distribution. The green density is our model, which is a single Gaussian. Because the data distribution is multimodal, our model does not have enough capacity to accurately capture it.
    Generating music in the waveform domain – Sander Dieleman
  • , GANs tend to be better at producing realistic examples, but worse at capturing the full diversity of the data distribution, compared to likelihood-based models.
    Generating music in the waveform domain – Sander Dieleman
  • Note that the density of a conditioning signal is often correlated with its level of abstraction
    Generating music in the waveform domain – Sander Dieleman
  • we can use logarithmically spaced quantisation levels instead to account for our nonlinear perception of loudness. This “mu-law companding” will result in a smaller perceived loss of fidelity than if the levels were equally spaced.
    Generating music in the waveform domain – Sander Dieleman
  • Note how the harmony is preserved, but the timbre changes completely.
    Generating music in the waveform domain – Sander Dieleman
  • they cover all the “degrees of freedom” that a performer has at their disposal
    Generating music in the waveform domain – Sander Dieleman
  • Perhaps most dramatic will be tragedies about dreamtime advocates who could foresee and were horrified by the coming slow stable adaptive eons, and tried passionately, but unsuccessfully, to prevent them
    This is the Dream Time | Robin Hanson
  • A governing principle is that 3 weeks, exactly 21 days—the period is curiously precise—is enough for recovery from the severest mental fatigue provided there is nothing pathological. This is expert opinion and my expertise agrees entirely, even to the point that, for example, 19 is not enough. Further, 3 weeks is more or less essential for much milder fatigue. So the prescription is 3 weeks holiday at the beginning of each vacation. It is vital, however, that it should be absolutly unbroken, whatever the temptation or provocation.
    Productivity advice | Zhengdong
  • some elements of ML we haven’t pinned down yet
    Skin is amazing, heals very quickly by reprogramming cells for transit
  • Deconvolution performs optimally for longer channels
    Data Export Pipelines