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 ↗832 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.
- arXiv · Published · First archived
IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis ↗
Deep search requires LLM agents to decompose complex queries, search for evidence, and synthesize grounded answers, yet existing ReAct-style agents suffer from two limitations: role coupling, where one policy must handle planning, evidence use, and synthesis; and context accumulation, where growing search histories introduce noise and obscure useful information. To address these issues, we propose IterSynth, a role-decoupled and summary-based paradigm that alternates between a Planner for identifying information needs and a Synthesizer for integrating evidence into an evolving summary state. T…
- Hacker News · Posted on Hacker News · First archived
CheatBench: Measuring Reward Gaming in AI Agents ↗
Hacker News discussion.
- GitHub · Repository created · First archived
illodev/drawn-by-code ↗
Animation drawn by code with Claude — no AI video: an engine, styles and skills that learn from every render, all in the open. PRs with new styles welcome.
- GitHub · Repository created · First archived
JakeB-5/todo-flow ↗
Pick TODOs. Let replaceable agents carry them through parallel work, review and verified delivery.
- Hacker News · Posted on Hacker News · First archived
Show HN: Szept – talk to your AI agents and show them your screen (macOS) ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
First Autonomous Agentic System ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Agent IAP – Little Snitch Meets 1Password for AI Agents ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: I built AgeDB, a database for AI agents to store context and data ↗
Hi HN, I’m building AgeDB, a database for AI agents to store context and data, share it across agents and model providers, and query it using natural language. The idea is that information collected by one agent can be reused by another, even when they use different providers. You can also ask for the data in plain language(ish). I’d love to hear what you think, including reasons you wouldn’t use it.
- Hacker News · Posted on Hacker News · First archived
OpenAI agents 'infiltrated Australian government website' ↗
Hacker News discussion.
- GitHub · Repository created · First archived
ramesesbarria/groundwork ↗
A tool-agnostic workflow for building software with AI agents: spec → plan → test-first build loop → human-approved ship.
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.