Tootfinder

Focus and Context and LLMs | Taras' Blog on AI, Perf, Hacks
#AI

Very interesting discussion!
https://www.thetransmitter.org/attention/the-brains-quiet-conductor-how-hidden-cells-fine-tune-arousal/

sp_high_school: High school temporal contacts (2013)
These data sets correspond to the contacts and friendship relations between students in a high school in Marseilles, France, in December 2013, as measured through several techniques.
This network has 329 nodes and 668 edges.
Tags: Social, Offline, Unweighted, Weighted, Temporal, Metadata

Fast Estimation of Globally Optimal Independent Contact Regions for Robust Grasping and Manipulation
Jonathan P. King, Harnoor Ahluwalia, Michael Zhang, Nancy S. Pollard
https://arxiv.org/abs/2506.08856

Fast Estimation of Globally Optimal Independent Contact Regions for Robust Grasping and Manipulation
This work presents a fast anytime algorithm for computing globally optimal independent contact regions (ICRs). ICRs are regions such that one contact within each region enables a valid grasp. Locations of ICRs can provide guidance for grasp and manipulation planning, learning, and policy transfer. However, ICRs for modern applications have been little explored, in part due to the expense of computing them, as they have a search space exponential in the number of contacts. We present a divide an…

Set Up a Recovery Contact for Your Apple Account
https://www.macrumors.com/how-to/set-up-recovery-contact-apple-account/

Set Up a Recovery Contact for Your Apple Account
Losing your Apple Account password can make your digital life a misery, as it can leave you locked out of the account that you use to manage your...

OpenAI's o3-pro is much smarter than o3 and amazing at using tools, but the model requires extensive context to perform optimally and may overthink without it (Ben Hylak/Latent.Space)
https://www.latent.space/p/o3-pro

God is hungry for Context: First thoughts on o3 pro
OpenAI dropped o3 pricing 80% today and launched o3-pro. Ben Hylak of Raindrop.ai returns with the world's first early review.

This https://arxiv.org/abs/2506.03100 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds
Retrieval-augmented generation (RAG) has seen many empirical successes in recent years by aiding the LLM with external knowledge. However, its theoretical aspect has remained mostly unexplored. In this paper, we propose the first finite-sample generalization bound for RAG in in-context linear regression and derive an exact bias-variance tradeoff. Our framework views the retrieved texts as query-dependent noisy in-context examples and recovers the classical in-context learning (ICL) and standard…

Memory cost of quantum contextuality with Pauli observables
Stefan Trandafir, Colm Kelleher, Ad\'an Cabello
https://arxiv.org/abs/2506.06869 https://…

Memory cost of quantum contextuality with Pauli observables
Classically simulating the quantum contextual correlations produced by sequences of ideal measurements of compatible observables requires the measured system to have an internal memory. Computing the minimum amount of memory needed is, in general, challenging. Here, building upon the work of Kleinmann et al. [New J. Phys. 13, 113011 (2011)], we prove that the memory cost for simulating the contextuality produced by the $10$ three-qubit observables of Mermin's pentagram is only $\log_2(5) \appro…

This https://arxiv.org/abs/2506.06266 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Cartridges: Lightweight and general-purpose long context representations via self-study
Large language models are often used to answer queries grounded in large text corpora (e.g. codebases, legal documents, or chat histories) by placing the entire corpus in the context window and leveraging in-context learning (ICL). Although current models support contexts of 100K-1M tokens, this setup is costly to serve because the memory consumption of the KV cache scales with input length. We explore an alternative: training a smaller KV cache offline on each corpus. At inference time, we loa…

Cloudflare open sourced an OAuth library mostly written by Claude, showing how AI handles mechanical implementation while humans guide with context and judgment (Max Mitchell)
https://www.maxemitchell.com/writings/i-read-all-of-cloudflares…

Max Mitchell's Personal Portfolio Website
Max Mitchell's personal portfolio website showcasing his photography, YouTube videos, coding projects, and work history.