Rememberbox

A text-first reading library
Saved751
Page5

2026-08-13

ArticleRead
GitHub - cordiverse/paper: A Programming Paradigm for Spatiotemporal Composability
GitHub
A Programming Paradigm for Spatiotemporal Composability - cordiverse/paper
--
GitHub - owenyuwono/poseidon: GPU-driven real-time FFT ocean (Three.js + WebGPU/TSL)
GitHub
GPU-driven real-time FFT ocean (Three.js + WebGPU/TSL) - owenyuwono/poseidon
--

2026-08-12

ArticleRead
yaniszaf.medium.com
yaniszaf.medium.com / source link only
--
DONUT: physics-aware machine learning for real-time X-ray nanodiffraction analysis
Cherukara, Mathew J. / Nature
Coherent X-ray scattering techniques are critical for investigating the fundamental structural properties of materials at the nanoscale. While advancements have made these experiments more accessible, real-time analysis remains a significant bottleneck, often hindered by artifacts and computational demands. In scanning X-ray nanodiffraction microscopy, which is widely used to spatially resolve structural heterogeneities, this challenge is compounded by the convolution of the divergent beam with
--
rd-signal-2: Frontier Classification at Production Scale
Ben Hylak, Manav Shah, Ryan D'Onofrio / Raindrop
A hybrid classification system that combines frontier-level judgment with the cost and speed required to run continuously in production.
--

2026-08-11

ArticleRead
Beautiful UI — Crafted primitives for AI-native interfaces
beautiful-ui-five.vercel.app
A small library of extremely crafted, copy-paste components for chat agents, thinking states, human-in-the-loop approvals, and everything agents need to talk to humans beautifully.
--
Can you reverse engineer an ASIC?
Jane Street Blog
Earlier this year we published a puzzle that handed you a complete neural network and asked you to figure out what it did. The response was great, so we’ve made another one! This time, we’re going much deeper down the tech stack.
--

2026-08-10

ArticleRead
Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents
[Submitted on 31 Jan 2026] / arXiv.org
Humans learn abstractions and use them to plan efficiently to quickly generalize across tasks -- an ability that remains challenging for state-of-the-art large language model (LLM) agents and deep reinforcement learning (RL) systems. Inspired by the cognitive science of how people form abstractions and intuitive theories of their world knowledge, Theory-Based RL (TBRL) systems, such as TheoryCoder, exhibit strong generalization through effective use of abstractions. However, they heavily rely on
--
Fast-growing hierarchy
Contributors to Wikimedia projects / Wikimedia Foundation, Inc.
From Wikipedia, the free encyclopedia
--
GitHub - johnazariah/emic: Epsilon Machine Inference & Characterization - A framework for computational mechanics
GitHub
Epsilon Machine Inference & Characterization - A framework for computational mechanics - johnazariah/emic
--
principles | Theophile Gervet
Theophile Gervet / theophilegervet.github.io
A collection of principles that resonate with me, in case you find it useful.
--
Waking Up with Neck Pain: Causes, Treatment, and Prevention
How we reviewed this article: / Healthline
Waking up with neck pain could be a sign that your pillow or sleeping position doesn't support your neck. Learn about all potential causes, plus treatment and prevention.
--

2026-08-09

ArticleRead
GitHub - duolahypercho/codex-router: External-model router for Codex with guided Kimi OAuth/API, DeepSeek, safe migration, and rollback.
GitHub
External-model router for Codex with guided Kimi OAuth/API, DeepSeek, safe migration, and rollback. - duolahypercho/codex-router
--

2026-08-08

ArticleRead
Autotelic Reinforcement Learning: Exploring Intrinsic Motivations for Skill Acquisition in Open-Ended Environments
[Submitted on 6 Feb 2025] / arXiv.org
This paper presents a comprehensive overview of autotelic Reinforcement Learning (RL), emphasizing the role of intrinsic motivations in the open-ended formation of skill repertoires. We delineate the distinctions between knowledge-based and competence-based intrinsic motivations, illustrating how these concepts inform the development of autonomous agents capable of generating and pursuing self-defined goals. The typology of Intrinsically Motivated Goal Exploration Processes (IMGEPs) is explored,
--
Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3
[Submitted on 30 Jul 2026] / arXiv.org
ARC-AGI-3 turns abstraction into an interactive problem of skill acquisition. A player must infer an unfamiliar game's rules, hidden state, and goal while maintaining action efficiency because every move counts. We formalize these environments as parameterized rendered deterministic Moore machines and introduce Tycho, a coding-agent system that constructs and uses game-specific models during interaction. Tycho separates actionable observations from intermediate animation, level-completion, and g
--
Core Concepts
DeepWiki / DeepWiki
This page explains the fundamental concepts of the Interaction Calculus (IC) and the theoretical underpinnings of the system implemented in this repository. It covers the core term representation, int
--
Open Policy Agent - Homepage | Open Policy Agent
www.openpolicyagent.org
--
Taste Is All That's Left
NotAShelf
On what is left to do once the machine can make anything, and why taste is the last craft worth keeping.
--

2026-08-07

ArticleRead
GitHub - andyzeng/tsdf-fusion: Fuse multiple depth frames into a TSDF voxel volume.
GitHub
Fuse multiple depth frames into a TSDF voxel volume. - andyzeng/tsdf-fusion
--
Backflip AI
www.backflip.ai
The AI copilot that CADs like a human. Backflip turbocharges your CAD and 3D modeling workflows, to help you design anything you can imagine. Spend less time on manual CAD tasks and more time building the physical world around you.
--
Energy — AI Assistants That Finish Your Work
getenergy.com
Energy is an AI workspace where specialized assistants complete work across your browser, inbox, files, and connected tools.
--

2026-08-06

ArticleRead
GitHub - carla-simulator/carla: Open-source simulator for autonomous driving research.
GitHub
Open-source simulator for autonomous driving research. - carla-simulator/carla
--
GitHub - louis-e/arnis: Generate any location from the real world in Minecraft with a high level of detail.
GitHub
Generate any location from the real world in Minecraft with a high level of detail. - louis-e/arnis
--
GitHub - cloudflare/cloudflare-os: Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems.
GitHub
Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems. - cloudflare/cloudflare-os
--
www.realtimerendering.com
www.realtimerendering.com / source link only
--