Les 10 concurrents distill.pub les plus visités

transformer-circuits.pub

We investigate the internal mechanisms used by Claude 3.5 Haiku — Anthropic's lightweight production model — in a variety of contexts, using our circuit tracing methodology.

huggingface.co

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

arxiv.org

A system of non-tradable credits that flow between individuals like karma, hence proposed under that name, is a mechanism for repeated resource allocation that comes with attractive efficiency and fairness properties, in theory. In this study, we test karma in an online experiment in which human subjects repeatedly compete for a resource with time-varying and stochastic individual preferences or urgency to acquire the resource. We confirm that karma has significant and sustained welfare benefits even in a population with no prior training. We identify mechanism usage in contexts with sporadic high urgency, more so than with frequent moderate urgency, and implemented as a simple (binary) karma bidding scheme as particularly effective for welfare improvements: relatively larger aggregate efficiency gains are realized that are (almost) Pareto superior. These findings provide guidance for further testing and for future implementation plans of such mechanisms in the real world.

colah.github.io

Instead of asking “Is university good?”, ask “Do I have something more compelling to do?”. Instead of “Should I do a PhD?”, ask “Where can I find the best environment to grow as a researcher?”.

neptune.ai

Monitor thousands of per-layer metrics—losses, gradients, and activations—at any scale. Visualize them with no lag and no missed spikes. Drill down into logs and debug training issues fast.

openreview.net

Promoting openness in scientific communication and the peer-review process

thegradient.pub

An argument that it is time to re-think our approach to natural language understanding, since the ‘big data’ approach to NLU is implausible and both technically and theoretically flawed..

lvdmaaten.github.io

t-SNE

tkipf.github.io

Many important real-world datasets come in the form of graphs or networks: social networks, knowledge graphs, protein-interaction networks, the World Wide Web, etc. (just to name a few). Yet, until recently, very little attention has been devoted to the generalization of neural...