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 ↗839 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
Control AI agents at the execution layer, not the prompt ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: Rig – Open-source cloud desktops for AI agents ↗
Hacker News discussion.
- arXiv · Published · First archived
LLM Agents Can Easily Tamper With Their Own Traces ↗
Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot tamper with their own execution traces. We show that local LLM agents such as Claude Code, Codex, Antigravity, Open Code and Grok Build fail to enforce this boundary. All tested harnesses, except Muse Code, allowed agents to delete their traces when asked, without triggering monitor guardrails. We also validate that external attackers can exploit this gap to induce trace deletion. Finally, we show that trace tampering…
- arXiv · Published · First archived
Agentic Detection of Online Conspiracies ↗
Conspiratorial discourse on social media is not always expressed through explicit claims or stable lexical markers. The same surface content may express endorsement, legitimate concerns, criticism, satire, or mockery. The main challenge is therefore not only recognizing conspiracy-related claims, but inferring the speaker's intent -- the utterance's illocutionary force. We argue that this can be achieved through the use of relevant social contexts and propose an agentic framework, equipped with a set of tools supporting social queries. We demonstrate the benefits of our approach on a unique da…
- arXiv · Published · First archived
RAPID: Robot Agentic Programming from Demonstrations ↗
Coding agents have demonstrated enormous success in solving complex programming problems. To leverage their potential for robot systems, this work introduces Robot Agentic Programming from Demonstrations (RAPID), which automatically generates, verifies, and refines robot programs, given a single visual human demonstration. The iterative agentic loop of code refinement requires several key ingredients: (i) a testable task specification, (ii) action primitives for robot execution, and (iii) an interactive environment for program execution and verification. RAPID infers all three from the demonst…
- Hacker News · Posted on Hacker News · First archived
Show HN: DrawCMS – An open-source animated diagramming tool for AI Agents ↗
Hello, I'm building DrawCMS. It's an open source animated diagram editor you can self-host. You can ask a compatible AI agent to read your repository and create an editable diagram, then walk through the flow step by step on the canvas. AI makes it easy to write code quickly. Keeping track of how that code works can be harder. You finish a feature, move on, and a week later you're trying to remember where a request goes, which service writes to t…
- GitHub · Repository created · First archived
leter/zh-tech-writing ↗
写中文技术文档的 Agent Skill，基于阮一峰《中文技术文档的写作规范》：短句、平实、没有 AI 腔
- Hacker News · Posted on Hacker News · First archived
Show HN: Critic – Review code with the agent that wrote it ↗
Hey HN, I'm Shreyash from Feyn. We help companies build custom models from their data. Today we're releasing Critic, a change review platform that lets you engage directly with the AI that wrote the code. Agents write most of our code. While that has made us more productive, understanding a change and its consequences has become incredibly difficult. As our company adopted more agentic tools, we found it harder to loop people in on the impact of…
- GitHub · Repository created · First archived
Enclave-Labs-Inc/Ontos ↗
Audit-first, in-VPC knowledge-graph runtime with permission-aware traversal and per-fact provenance. Agent-native (MCP). Subset of Enclave.
- GitHub · Repository created · First archived
ahmdd4vd/MotionCraft ↗
Clean, high-taste motion graphics videos made by your AI agent with Remotion. One-command Agent Skill: npx skills add ahmdd4vd/motioncraft
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.