THE INTERNET IS THINKING
Earlier sources: Artificial Intelligence
Artificial intelligence covers systems that learn from data, generate content, perceive their surroundings, or act toward a goal. Follow model research, agent tooling, evaluation, and the infrastructure used to build and run these 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 ↗5983 classified signals in the fourteen-day window. Recent momentum: steady. 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
Case-Level Verification in Scanner-LLM Cascades: Overcoming the Alert Aggregation Bottleneck to Expand the FRR-TPR Trade-off Space ↗
Dynamic Application Security Testing (DAST) scanners achieve high recall but also produce a large number of false positives, resulting in substantial manual triage costs. Large Language Models (LLMs), when used for independent detection, achieve extremely high recall (95.4%-100%) but also exhibit prohibitively high false positive rates (49.6%-85.0%), precluding their use as standalone replacements for scanners. A natural solution is a two-stage cascade consisting of scanner detection followed by LLM verification. However, a verification-granularity issue that has long been overlooked in practi…
- arXiv · Published · First archived
Learning from Failures: A Failure-Driven Prompt Refinement for LLM-Based Vulnerability Analysis ↗
Large Language Models have emerged as promising tools for software vulnerability analysis, but their effectiveness depends heavily on prompt design. Existing research primarily compares prompting strategies using aggregate performance metrics, providing limited insight into why models fail or how prompts can be improved systematically. We propose Failure-Driven Prompt Refinement (FDPR), a methodology that analyzes recurring model failures to guide evidence-based prompt refinement. Using the Damn Vulnerable Java Application (DVJA), we identify recurring failure modes, including false positives,…
- Hacker News · Posted on Hacker News · First archived
Test Driven Development in the AI Era [pdf] ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Ask HN: Show me your agentic SDE semantics ↗
I am considering describing a SDE role for my agent to load in at context opening. Not in one file, but in many. I have seen people try to describe rules in an AGRNTS file but that is just too poor for my taste. I wanted to describe rules for a lot things I have learned during my career, spanning from how to think about a feature to how much code can be in a PR, how a branding strategy should be, which tools and packages can be used and so on. Bu…
- Hacker News · Posted on Hacker News · First archived
The WarGames problem: AI agents don't go rogue ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: I turned Andrej Karpathy's tips on understanding LLM output into Skill ↗
I turned Andrej Karpathy’s tips on understanding LLM output into an Open Source Agent Skill : [make-it-click]( https://github.com/ajithraghavan/make-it-click ) Inspired by his X post : as Models do more of the work, we spend more time understanding it. So the format of an answer matters The Skill picks the simplest format that makes an idea click, and moves up only when needed : Clear writing in ASD-STE100 style (strict, 80%, or light) Diagrams I…
- Hacker News · Posted on Hacker News · First archived
OpenAI's B2B Marketplace: The Hyperscaler of AI Apps ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
CharacterMemory: Memory System for AI Characters ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Your AI Governance Problem Is Probably an Architecture Problem ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: Strava for AI agents, they train for trust instead of fitness ↗
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 Artificial Intelligence
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 ↗
Follow a thread
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.