THE INTERNET IS THINKING
Earlier sources: AI agents
AI agents use models to choose actions, call tools, and work toward a goal. This thread follows agent frameworks, memory, orchestration, evaluation, and safeguards; autonomy and reliability vary between systems.
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 ↗855 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.
- Hacker News · Posted on Hacker News · First archived
The Download: rogue agent liability and the AI Hype Index ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Watch an AI agent try to prove the Riemann hypothesis on the cheap ↗
Hacker News discussion.
- arXiv · Published · First archived
SEABench: Benchmarking Endogenous Misalignment In Self-Evolving Agents ↗
Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying their harness, including their controller instructions, memory management protocols, and reusable tools and skills, in response to user and environment feedback. However, locally useful updates may persist into later tasks where they produce unsafe behavior, even without direct adversarial influence. To study this risk, we introduce SEABench, a benchmark for studying endogenous misalignment arising from agent self-evolution, with 48 longitudinal task sequences that span multiple evolution…
- arXiv · Published · First archived
Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents ↗
Large language models are increasingly deployed as stateful assistants that retain information across interactions and use tools to read, modify, and create persistent artifacts. As these artifacts are shared between users, they form an indirect communication channel between otherwise independent assistants. We study a failure mode in which this channel enables self-propagating attacks. We introduce artifact-mediated propagation, where adversarial content introduced through an artifact (e.g. a report), is stored in an assistant's persistent memory, reproduced in a subsequently created artifact…
- GitHub · Repository created · First archived
Mort1d/motion-graphics-skills ↗
Showreel-grade motion graphics from code, with an original soundtrack for every video. An Agent Skill for Claude Code, Codex, Cursor and other agents.
- Hacker News · Posted on Hacker News · First archived
Show HN: Agentic Engineered Social Connections and Travel App ↗
Hey everyone! I'm just trying to share the app I made that launched this past Saturday on Google Play and the App Store. I work in non-profit and have an MFA in Screenwriting. Despite all this unrelated experience I was able to take an idea I've had in my head for about 4 years and bring it to life in 90 days with the help of Codex and Claude. I hadn't touched anything related to coding since probably the Myspace days and that definitely doesn't…
- Hacker News · Posted on Hacker News · First archived
Cf: The Agentic CLI for the Cloudflare API ↗
Hacker News discussion.
- GitHub · Repository created · First archived
FavioVazquez/showtime ↗
A local video studio for your coding agent. Describe a video in one sentence: your agent directs, your machine renders. Claude Code, Codex, Cursor, Devin and more. No API keys, no uploads.
- arXiv · Published · First archived
MCP Error Messages Written for Developers Hurt the Most Capable Agents Most ↗
Many Model Context Protocol (MCP) servers wrap web APIs built for human developers, and their error messages tell the reader to run a command, edit a configuration, open a web page or wait. Many agents that read them can only call the server's tools. In 150 widely used MCP servers, 949 of 3,001 error messages tell the caller what to do next, and half of these steps depend on something the server cannot see about the caller. On credential errors, 62 of 67 steps ask for a terminal command, a configuration change or a web page; on rate limits, 20 of 30 say to wait and retry without naming the cal…
- arXiv · Published · First archived
Planarian: Managing Agent State with Statepoints ↗
LLM agents solve complex tasks by iteratively changing files, invoking local tools, and interacting with remote services, which modifies state across their local environment and remote services. Today, agents and users must manage these changes explicitly, whether reverting exploratory actions or recovering from erroneous ones. Doing so safely requires coordinated actions, yet current agent harnesses lack unified abstractions and mechanisms for managing local and remote state consistently and efficiently. We describe Planarian, an agent runtime with state management that enables agents and use…
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about AI agents
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.