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 ↗6007 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.
- Hacker News · Posted on Hacker News · First archived
How (and Why) to Build an AI Agent from Scratch in Python ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
OntoPrune – Pruning 85% LLM context tokens and 6.7x TTFT on CPU ↗
Hacker News discussion.
- arXiv · Published · First archived
Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents ↗
Autonomous coding agents now resolve a substantial share of real-world GitHub issues. However, passing functional tests differs fundamentally from producing a high-quality contribution acceptable for merging. Mature open-source projects publish repository-specific contribution policies, spanning style, git, testing workflows, to ensure code quality and long-term maintainability. Because existing benchmarks evaluate patches solely on unit tests, agent compliance with repository governance remains unknown. In this paper, we introduce SWE-CC, a benchmark evaluating code and process compliance in…
- Hugging Face · Model / dataset date · First archived
dendriteholdings/albedo — dataset update ↗
# albedo — SWE-agent reference trajectories Reference trajectories from SN97 (albedo) evaluations. Each row is a chat-format sample: - `sample_id` — source shard and row of the underlying task (` / .parquet: : `) - `messages` — `list `: a `system` prompt, the `user` task (PR description + instructions), then alternating `assistant` reference steps and `user` environment observations - `run` — which of the sample's reference runs this row is (1-3) - `made_edit` — whether the run changed any file (null for rows recorded before 2026-09-22) - `score` — the run's score on the sample's final checkli
- Hugging Face · Model / dataset date · First archived
OliviaRossi/Gemma-4-12B-it-QAT-Q5_K_L-MTP-GGUF — model release ↗
Hugging Face Collection • GitHub • DeepMind Blog • Documentation # Gemma-4-12B-it-QAT-Q5_K_L-MTP-GGUF High-precision **Q5_K_L** GGUF quantizations of Google's official Quantization-Aware Trained (QAT) Gemma 4 12B model, complete with its official **Multi-Token Prediction (MTP)** drafter head and **Multimodal Projector (mmproj)** for vision and audio understanding. ## Repository Files | Filename | Role | Size | Description | | :--- | :--- | :--- | :--- | | **`gemma-4-12B-it-qat-Q5_K_L.gguf`** | Target Model | ~9.1 GB | Base model with `Q5_K_M` attention/MLP and lossless `Q8_0` embeddings & LM h
- Hugging Face · Model / dataset date · First archived
mradermacher/torchcast-decision-27b-i1-GGUF — model release ↗
## About weighted/imatrix quants of https://huggingface.co/torchcast-ai/torchcast-decision-27b ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#torchcast-decision-27b-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/torchcast-decision-27b-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/torchcast-decision-27b-GGUF).** ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/Th
- Hacker News · Posted on Hacker News · First archived
Do people prefer stories written by AI? ↗
Hacker News discussion.
- Hugging Face · Model / dataset date · First archived
caiovicentino1/Ekbasis-27B — model update ↗
# Ekbasis-27B — an open world model for agents  **Paper:** [Look When Unsure, Check When Sure](https://doi.org/10.5281/zenodo.23146971) · DOI [10.5281/zenodo.23146971](https://doi.org/10.5281/zenodo.23146971) · **Code:** [github.com/OpenInterpretability/ekbasis](https://github.com/OpenInterpretability/ekbasis) · **Site:** [openinterp.org/ekbasis](https://openinterp.or
- Hacker News · Posted on Hacker News · First archived
Show HN: Lazychat – A lazygit-style TUI for running Claude Code and Codex ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: Jamming with Jev and Claude on TidalCycles ↗
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.