THE INTERNET IS THINKING
Earlier sources: AI research
AI research investigates learning algorithms, model behavior, evaluation, and the limits of intelligent systems. Follow original papers and research artifacts; preprints may change and are not necessarily peer reviewed.
SYMTRI organizes observations from public sources into a living map. Connections reflect shared subject matter; they do not establish causation or endorse a source.
Open in the map ↗48 classified signals in the fourteen-day window. These counts include signals awaiting readable evidence.
Earlier sources
Up to ten sources with readable evidence, ordered by their feed timestamp. These archive sources can be older than the live fourteen-day window. This list is a sample, not a measure of total activity. Dates distinguish paper publication, repository creation, model/dataset activity, Hacker News posts, and KEV catalog additions. “First archived” records when SYMTRI first stored the signal.
- GitHub · Repository created · First archived
Edwardxlai/easyread ↗
把英文论文读成舒服的中文：本地 PDF 论文翻译、原文对照、边读边问 AI、文献管理。Read English papers in comfortable Chinese.
- GitHub · Repository created · First archived
e2sy/jailbreak-archives ↗
A structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-teaming, and defensive hardening.
- arXiv · Published · First archived
DAGent: Evaluate-then-Grow Planning for Deep Research Agents ↗
Deep research tasks require agents to navigate large knowledge spaces, synthesize evidence across many sources, and adapt their plans as findings emerge. Directed acyclic graph (DAG)-based multi-agent systems suit this setting because they support parallel execution and isolate each sub-task within a focused dependency context. Yet existing DAG-based agents instantiate a task-level plan before execution and repair the graph only after failures or missing evidence are observed. This Plan-then-Patch strategy is brittle for deep research: the system commits most strongly when its evidence is weak…
- OpenAlex · Published · First archived
DAIMON: Designing AI-Augmented Research Dashboards to Enable Novel Human-AI Collaborative Workflows in Longitudinal Sensing Studies ↗
Researchers conduct longitudinal passive sensing studies in in-the-wild settings, often spanning months or years, to uncover naturalistic behavioral patterns. These studies are not “set-and-forget” deployments; they require continuous monitoring as technical failures and declining participant compliance can lead to substantial missing data, undermining study validity and downstream models. Thus, conducting these studies involves multiple detail-oriented, cognitively demanding, and time-consuming tasks, making it a burdensome and stressful process. Existing research dashboards, the primary tool…
- Hacker News · Posted on Hacker News · First archived
An LLM Workflow That Reproduces, Improves, Extends Published Economics Research ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
CoreWeave ARIA: AI Research and Iteration Agent ↗
Hacker News discussion.
- GitHub · Repository created · First archived
mikamikasuki/FOREST ↗
FOREST is a research agent for long-horizon science, where evidence gets lost, errors compound, and goals drift. It explores ideas, reads literature, forms hypotheses, runs real experiments, analyzes results, revises paths, and builds a full paper—all in an editable graph you can inspect, branch, redirect, with claims and figures linked to evidence
- arXiv · Published · First archived
pikit: A Composable Toolkit for Indirect Prompt Injection Research and Evaluation ↗
Indirect prompt injection embeds malicious instructions within external content retrieved by LLM-based agents, altering target behavior without user authorization. We introduce pikit, a research toolkit designed to systematically evaluate these threats across three core dimensions: attacks (13 methods), channels (16 carriers across text and file modes), and defenses (9 prevention strategies and 3 offline detection baselines). Built on a decorator-based registry, pikit enables seamless extension of custom components without modifying core code, while a unified craft() API composes arbitrary att…
- OpenAlex · Published · First archived
Artificial intelligence, augmented reality, and virtual reality in science education: scientific mapping and future research ↗
Abstract This study examines the trends, thematic development, and research collaboration patterns related to Artificial Intelligence (AI), Augmented Reality (AR), and Virtual Reality (VR) in science education through a comprehensive bibliometric analysis. The rapid integration of these emerging technologies has increased the demand for innovative learning approaches capable of enhancing student engagement, conceptual understanding, and immersive learning experiences in science education. Bibliometric analysis was conducted using Scopus-indexed publications from 2014 to 2024, comprising 196 ar…
- Hacker News · Posted on Hacker News · First archived
Stephan Wolfram on the Future for Math Research in the Age of AI ↗
Hacker News discussion.
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about AI research
Check each original source for its methods, release status, limitations, and supporting data. A repository announcement, a preprint, and a published study provide different kinds of evidence. SYMTRI’s subject classification helps discovery; it does not independently validate the source’s claims.
See the collection and counting methodology ↗ · Read the weekly synthesis ↗
Related threads
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.