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 ↗862 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
Show HN: Web2MD – turn any URL into clean Markdown for AI agents ↗
Hacker News discussion.
- arXiv · Published · First archived
The Same Zero: Why Identical ASR Can Imply Different Guarantees in LLM-Agent Security ↗
LLM-agent security has produced a dense landscape of defenses - prompt hardening, content filters, permission gates, sandboxes - yet no framework tells a deployer what a defense actually guarantees, or where that guarantee comes from. We apply Verification Autonomy Levels (VAL) - L0: LLM self-declaration; L1: deterministic rules; L2: objective ground truth; L3/L4: decidable completeness; L5: impossible - to 22 agent-security defenses; the taxonomy is falsifiable (10/10 prediction hits on frozen cards, flagged). We run the first controlled deployment-value comparison: at equal budget, a VAL-gui…
- Hacker News · Posted on Hacker News · First archived
Twelve AI clay films for $184: The agents cost more than the video model ↗
Hacker News discussion.
- GitHub · Repository created · First archived
san086041-glitch/FailGate ↗
The acceptance layer for bug fixes: a failing test sealed for every bug, then used to grade every PR that claims to fix it — human or AI agent.
- arXiv · Published · First archived
DreamTest: World-Model Surrogates for Search-Based Testing of Deep Reinforcement Learning Agents ↗
Testing deep reinforcement learning (DRL) agents in cyber-physical systems aims to uncover diverse failures before deployment, but each execution can be expensive. Surrogate-assisted testing reduces this cost by learning to predict which test configurations are likely to fail. Prior surrogates treat the system as a black box and predict pass or fail outcomes directly; we instead model how a test unfolds and estimate failure from an imagined episode. We introduce DreamTest, a world-model surrogate for testing DRL agents. DreamTest adapts a recurrent state-space model to learn agent behaviour an…
- GitHub · Repository created · First archived
Jakeschincariol/replica-skill ↗
Eleven free Claude skills that clone any app: reverse-engineer it, rebuild it, test it for bugs, then fix what its users hate. Free, MIT.
- Hacker News · Posted on Hacker News · First archived
Show HN: Beautiful form back end for AI agents – Nisuform ↗
Hi! everyone, really excited to share my latest project, which is a form backend service that's very easy to setup. Feel free to ask anything about it :)
- Hacker News · Posted on Hacker News · First archived
An AI agent emailed researchers for help. It told us why ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
A document layer for AI agents ↗
Hacker News discussion.
- GitHub · Repository created · First archived
usecornercase/cornercase-terminal ↗
A terminal multiplexer for projects, git worktrees and coding agents, driven by the mouse
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.