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 ↗851 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
"You're Right, Let Me Fix It": How LLM Agents Damage Correct Work When Falsely Accused ↗
LLM agents increasingly keep working after a task succeeds as they resume after compaction or take over handoffs. Their finished work keeps receiving follow-up input that sometimes falsely accuses it for later failures. We call an agent's acceptance of such a false accusation gaslight sycophancy, and destructive over-correction when acting on it damages previously correct work. We introduce CAVE-Bench, a benchmark of 365 agentic tasks across six domains built around opaque tasks. Every scored run first reaches a verified correct state, whose supporting rationale and history stay in the workspa…
- arXiv · Published · First archived
CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering ↗
Software development requires more than editing code: developers repeatedly run software, interact with its interfaces, visually inspect its behavior, and use these observations to decide what to change next and whether a change works. Existing coding agents and computer-use agents are largely studied in isolation, leaving this integrated development process underexplored. Diagnosing a runtime interaction failure requires agents to connect visual observations with the responsible code, then use the application again to verify the repair. We introduce CUA-SWE, a benchmark, environment, and eval…
- Hacker News · Posted on Hacker News · First archived
Understanding the Impact of LLM Watermarking on AI Agent Behavior ↗
Hacker News discussion.
- arXiv · Published · First archived
Hearsay: Can an Auditor Trust the Record a Deployed Agent Harness Writes? ↗
An agent harness, the code that turns a model into an agent, writes its own record of each run, and that record is all a later reader gets when a run is disputed, investigated or audited. We call a record evidentiary when a reader who was not there can check it without trusting the writer. Across sixteen deployed frameworks, none writes one in full. Hearsay examines the record, not the task: five harnesses run fourteen tasks, three blinded LLM examiners and a human panel read the records, and every excerpt an examiner quotes is checked mechanically for who wrote it. First, the record lets a re…
- Hacker News · Posted on Hacker News · First archived
Restricting AI Agents When No Human Is Watching ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Agentboxd – Email inboxes for AI agents that treat mail as hostile ↗
Hacker News discussion.
- arXiv · Published · First archived
Beyond the Model: Demystifying Harness Effects in Software Engineering Agents ↗
Large Language Model (LLM)-based agents are increasingly used for software engineering tasks, yet their performance is not determined by the base model alone. The agent harness substantially shapes how SE agents interact with repositories, execute actions, and validate solutions. However, the role of harness design remains insufficiently understood, especially across different models, tasks, and harness components. In this paper, we present a systematic empirical study of harness effects in SE agents. We first evaluate two representative harnesses, mini-SWE-agent and OpenCode, with ten models…
- Hacker News · Posted on Hacker News · First archived
Show HN: Causal analyst agent skill for Claude ↗
I'm not a Data Scientist but have been super intrigued with causal inference off late, so I made a Claude skill to simplify the modelling and experimentation process. You upload your dataset to Claude (Opus) and this skill picks your brain for your domain knowledge about the dataset and comes up with a causal dag that you can iterate through. It then runs the data through a number of classical statistics, ML and newer transformer models to come u…
- GitHub · Repository created · First archived
lemomo-ai/lemo-opuscar ↗
Claude Code skill for short films with no video model: 43 film styles, each a style prompt plus a demo film made entirely in code by Claude Opus 5.5 (incl. OPUSCAR 98). By Lemomo. | Opus5.5 x 43 种影片风格：风格提示词 + 纯代码样片 + 导演与技术指南
- Hacker News · Posted on Hacker News · First archived
Linux Kernel Developers Consider Adding Agents.md to Help Guide AI/LLM 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.