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 ↗5982 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
PatchHolmes: Agentic Patch Retrieval via Listwise Selection ↗
Patch retrieval, the task of finding the commit that fixes a known vulnerability, is the foundation of vulnerability management workflows, yet 60% to 63% of CVEs in the major advisory databases lack a patch link. We present PatchHolmes, a two-phase patch retrieval system that pairs a hybrid first-stage retriever with an agentic second-stage inspection loop. Unlike pointwise prior work that scores each candidate independently, the Phase 2 agent reads the top-100 listwise: it sees the full candidate list at once and selectively reads 3 to 10 commits through four budgeted tools before submitting…
- Hacker News · Posted on Hacker News · First archived
Responsible Release of AI-Generated Mathematics ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: Moching – AI desktop agent with 219 built-in tools (Rust) ↗
Hacker News discussion.
- Hugging Face · Model / dataset date · First archived
drzo/echoself — model update ↗
# EchoSelf NanEcho Model ## Model Description This is a **Deep Tree Echo** cognitive architecture model trained using the EchoSelf framework. The model implements adaptive attention mechanisms, persona dimensions, and recursive reasoning capabilities inspired by cognitive science and AGI research. ## Model Architecture - **Base Architecture**: GPT-2 - **Parameters**: 4 layers, 256 embedding dimensions - **Vocabulary Size**: 50257 - **Context Length**: N/A tokens ## Training Details - **Checkpoint ID**: ckpt_20260930_015911_4500_46032ab3_9470fbb7 - **Training Iteration**: 4500 - **Validation Lo
- arXiv · Published · First archived
Adaptive-GEPA: Make Your Harness Fit Heterogeneous Requests ↗
Reflective optimizers such as GEPA improve language model prompts from execution traces and evaluator feedback; full-program extensions can also rewrite tools and control flow. In practice, a user hands the same endpoint heterogeneous requests whose effective solutions require different tools, reasoning modes, and control flow. Optimizing one shared program leaves this division of work implicit in source-code search, while optimizing a separate program per request family fixes it beforehand. We introduce Adaptive-GEPA, which learns both how to divide requests and how to solve them. It evolves…
- Hacker News · Posted on Hacker News · First archived
Thinking out loud AI and Cancer Cure ↗
Anyone else ever think how every week there's another article and news story about how advanced AI is getting and how fast it's progressing, usually reported as a threat to society. If it is so alarmingly powerful, why has a super genius not OP'd on Opus 5.5 Max and discovered a cure for cancer or some horrible disease... I use my AI good for making dashboards and looking at spreadsheets, call to the super geniuses who are also scientists please…
- Hacker News · Posted on Hacker News · First archived
Diffsmith AI Code Review Tool ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
LabBench: Can AI agents decide what experiment to run next? ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Vibe Coding Discover – A Catalog of AI OSS for Agents, MCP, Skills, RAG ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: InfiniHash App Store – compliance tools built end-to-end by AI 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 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.