IdeaRadar

Building AI agents, previously AI/ML at big tech. In my spare time explore the intersection of society, computers, complexity, and intelligence.

[IdeaRadar @idearadar]

@_M_Mountain_ Look up Anatolian Neolithic Farmers or Early European Farmers for more: https://t.co/tVzjd5kmQ0

[Ancestral Whispers @Sulkalmakh]

1. Map of Anatolia_N/ANF/ENF admixture.
2. Man from Neolithic Greece.
3. Man of Linear Pottery Culture.
4. Woman from Neolithic Czechia.

[IdeaRadar @idearadar]

@_M_Mountain_ Haber, Marc, et al. "Genetic evidence for an origin of the Armenians from Bronze Age mixing of multiple populations." European Journal of Human Genetics 24.6 (2016): 931-936.

[IdeaRadar @idearadar]

@RokoMijic Western democracy worked not by accident, but by getting pretty close to a "self-organized critical state" in social and economic dynamics (in complete opposition to communist or fas#ist states), and it's moving away from this state due to ossified bureaucracies, wear & tear.

[IdeaRadar @idearadar]

@RokoMijic If your world model gives a ridiculously low P(data|model) estimate, you need to update the model, not make a strange claim along the lines of "the world keeps throwing 6-sigma events at me!" (as is done regularly in finance when gaussians are used where they shouldn't be).

[IdeaRadar @idearadar]

@3N717Y7 @edodreaming @BlkPHomo @eyeslasho @VictimaeLaudes My point is that sides are really about "I want to keep the hierarchy/status quo" and "I want to topple the hierarchy/status quo". It's just a matter of which variables you're projecting onto, when mentally simulating your prospects under each scenario.

[IdeaRadar @idearadar]

@3N717Y7 @edodreaming @BlkPHomo @eyeslasho @VictimaeLaudes I think centrism is an unstable equilibrium point. In the end, you either like your prospects in a particular projection of the societal monkey hierarchy you're in, or you don't. Centrism means you haven't felt strong emotions about your position in this hierarchy yet.

[IdeaRadar @idearadar]

@drvineetgovinda @JessePeltan Make it *exactly* the same size as the image of the aforementioned giant fusion reactor as seen from the planet, causing a zero-probability event called total eclipses, so that any remotely intelligent species is left with no doubt of the artificiality of the whole construction.

[IdeaRadar @idearadar]

@IntuitMachine This is a linguist's roadmap. These models are still inherently interpolators-only and language-scale focused.

[IdeaRadar @idearadar]

https://t.co/kW2iJ6GoVw

[Valentino Maiorca @ValeMaiorca]

📢 It looks like relative representations are here to stay!

I'm beyond thrilled to announce that our work has been selected as one of the notable top 5% (oral) papers at #iclr23 ! 🥳

https://t.co/nlZBiaIMHZ

[1/5]

[Anthropic @AnthropicAI]

We have little mechanistic understanding of how deep learning models overfit to their training data, despite it being a central problem. Here we extend our previous work on toy models to shed light on how models generalize beyond their training data.
https://t.co/0bYUToop3m

[Anthropic @AnthropicAI]

Neural networks often pack many unrelated concepts into a single neuron – a puzzling phenomenon known as 'polysemanticity' which makes interpretability much more challenging. In our latest work, we build toy models where the origins of polysemanticity can be fully understood.

[Mark Riedl @mark_riedl]

Working on a walkthrough of transformer code with side-by-side comparison to the computation graph. Felt the default image everyone uses is hard to interpret. Also, I like to show the matrices in my computation graphs. § refers to sections in a colab notebook (coming soon)

[IdeaRadar @idearadar]

@jessald @psychosort Over what timescale? They work catastrophically poorly from where I stand

[IdeaRadar @idearadar]

@GopackgoGPG @mattwwaters @blankboijanjan @Richlin2000 @RampCapitalLLC That would be the sharpness of the toys, duh