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 ↗856 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
Trust Is Not a Score: Runtime Assurance Contracts for High-Risk AI Agents ↗
Benchmarks, audits, and agent protocols describe performance, permissions, and repair, but not how observed evidence should change an agent's authority during a consequential task. We call this the assurance-transition gap. We propose a Runtime Assurance Contract (RAC), a policy-level formal schema binding autonomy boundaries, component eligibility, evidence state, transition policy, human-review capacity, and non-compensatory gates. Under RAC, soft metrics may inform routing, whereas a failed or unknown mandatory gate forces retry, switch, escalation, deferral, or stop; aggregate performance…
- GitHub · Repository created · First archived
flaviocopes/skillscout ↗
Find the skills your coding agents load, see which agents can use each one, and count how often you use them
- GitHub · Repository created · First archived
adityaagarw/Pantheon ↗
A 3D world where AI agents live, work and teach, and you can watch everything they do. Self-hosted, works with local models.
- Hacker News · Posted on Hacker News · First archived
ADLX 2.0: Extending graphics control to AI agents and agentic apps ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: SFML – A markup language for software factories, Terraform for agents ↗
SFML is a language specification for defining software factories. You can think of it as Terraform for your software development lifecycle. I started from a language spec to help think through both how a factory is defined and how a conforming runner processes it. The push to do this comes from leading teams where everyone has a unique coding setup, which results in different agentic coding processes. People also want to work together on improvin…
- Hacker News · Posted on Hacker News · First archived
Show HN: Four frontier models argue over your AI agent's riskiest code ↗
Hacker News discussion.
- arXiv · Published · First archived
Pretext: Defeating Malicious Skill Detection Frameworks for AI Agents ↗
Skills extend an agent's capabilities by injecting instructions and information into the context, and are widely used by agents such as OpenClaw and Claude Code. Prior work shows third-party marketplaces host malicious skills that give attackers direct influence over the victim's agent. The emerging defense scans skills before installation, pairing deterministic static checks with an LLM-based semantic judge, as in NVIDIA's SkillSpector. We show that such defenses fall to an attacker who knows the detector. Our white-box LLM attacker, Pretext, iteratively crafts skills that evade detection whi…
- Hacker News · Posted on Hacker News · First archived
Show HN: FinTrace – point-in-time guardrails for financial LLM agents ↗
Hacker News discussion.
- GitHub · Repository created · First archived
justxor/claude-code-pro-course ↗
Claude Code PRO — полный курс и гайд на русском: CLAUDE.md, settings, skills, subagents, hooks, MCP, плагины, CI. 8 лабораторных, библиотека промптов и готовый starter-kit https://t.me/ai_machinelearning_big_data/10997 - здесь бесплатные курсы по chatgpt
- arXiv · Published · First archived
Speculative Safety Honeypot: Toward Proactive Defense Against Multi-turn Agent Attacks ↗
As Large Language Model (LLM) agents are increasingly deployed in complex environments, multi-turn interaction attacks have become a significant security challenge. Existing detection methods typically rely on historical context. However, this retrospective logic struggles to identify deep malicious intents that are split across turns to hide future risks. Inspired by speculative decoding, we propose the Speculative Safety Honeypot (SSH) framework. SSH uses a multi-agent simulation system composed of small LLMs to build an action-level speculate-and-verify workflow. In the speculation stage, S…
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.