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
Doubts grow over claims OpenAI agent hacked Australian Medicare portal ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: Worktable, an open-source workspace for you and your agents ↗
Hello HN! I built Worktable as an open-source, file-based workspace for you and your agents to create docs, plans, and build small tools. For example, you ask an agent to compare hosting options for your next side project, save the research notes, and build a calculator where you can adjust traffic and storage assumptions yourself. As a backstory, I run my Claude Code, Codex, and OpenClaw on a server at home and was consistently frustrated with t…
- GitHub · Repository created · First archived
looper42/mobile_agent ↗
An open-source Android AI agent that operates your phone in the background, with local models, tool calling, and automated task execution.
- Hacker News · Posted on Hacker News · First archived
Show HN: Threshold Cryptography for AI Agents Using Payments and Digital Assets ↗
We introduce the concept of a "cryptographic identity", which consists of a private key, a manifest attached to it that defines what a specific action is allowed or not allowed to do, and additional controls. The principle is simple: when an AI wants to perform an action, it has to request a signature for that action, and the signature is issued only after the checks pass. I think this approach is flexible enough for most use cases, while also im…
- GitHub · Repository created · First archived
Protocol-Lattice/harness-router ↗
A decision layer embedded into the harness tool-selection loop
- GitHub · Repository created · First archived
YeJe-cpu/SeeCut ↗
An AI editor that watches its own cut: talking-head / AI-avatar video → auto-edited short video. 网感口播精剪：数字人/真人口播 → AI 自动精剪成网感动效短视频 → 可选剪映分层草稿
- Hacker News · Posted on Hacker News · First archived
Show HN: Agentic CUDA Kernel Optimizer ↗
Hello; I was working on optimizing some CUDA kernels and I thought may be it is a good oppurtunity learn langgraph as well. I created a simple C++ CUDA Test Harness and handed that to AI agents. They can run kernels, get benchmarks, and even can profile via nsight
- GitHub · Repository created · First archived
mirkobozzetto/bunflared ↗
One command, one throwaway public link for your localhost, several ports behind it (your app and its API). Then run your demo live: chat with your client from the terminal, send them to a page, follow their cursor, catch their reactions and notes as they happen 🔥 Soon your coding agent runs the session for you.
- GitHub · Repository created · First archived
omnesis-dev/Omnesis ↗
Index, search, and reason about your entire digital life.
- Hacker News · Posted on Hacker News · First archived
Show HN: AtlasBurn – Know what your AI costs and stop runaway agents ↗
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.