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 ↗853 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
FrederikRogalski/tinycoral ↗
tinygrad on Google's Coral Edge TPU: reverse-engineered ISA, our own code generator and USB driver. A whole transformer runs on the stick. Written by AI agents.
- arXiv · Published · First archived
EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents ↗
Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resources. Existing benchmarks leave gaps in executable coverage of their runtime security risks, while evolving model capabilities, harnesses, tools, and threats motivate benchmark evolution. We introduce EvoRiskBench, an evolving benchmark organized around the EP-Path-EF framework, which links an initial risk entry point to a one-hop technical effect through an agent-mediated risk path. The framework defines nine entry-point categories and five effect c…
- GitHub · Repository created · First archived
pooops15/muse-bridge ↗
Turn Muse (AI agent) into an OpenAI-compatible model (ms/muse) inside self-hosted 9Router for Hermes — file-queue bridge with native tool calls, unlimited batching & image understanding. Beginner tutorials in English & Indonesian
- Hacker News · Posted on Hacker News · First archived
How we built olddogs.ai with lots of agents but zero slop ↗
Hacker News discussion.
- arXiv · Published · First archived
Securing Computer-Use Agents Against Branch Steering Attacks ↗
Modern Computer Use Agents (CUAs) directly interact with graphical user interfaces and execute third-party web tools, exposing them to indirect prompt injection across every rendered page and tool response. While the Dual-LLM pattern is the primary system-level architecture offering formal security guarantees - using an isolated Planner LLM (P-LLM) to fix execution paths before processing untrusted inputs via a Quarantined LLM (Q-LLM) - these guarantees break down in graphical environments. Because CUA interaction is inherently dynamic, plans cannot remain data-independent; they must branch ba…
- GitHub · Repository created · First archived
QingYunA/answer-me-with-html ↗
Answer me with HTML — an agent skill that answers hard questions with a one-page HTML you can actually read. 让 AI Agent 用一页 HTML 回答复杂问题。
- Hacker News · Posted on Hacker News · First archived
GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: Agent-Chrome – Claude Code browses in Chrome without stealing focus ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Agentic Runtime: Python Startup Time and Import Optimization (4s –> 2s) ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Below Intent: The Semantic Infrastructure of Agentic Software Engineering ↗
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 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.