THE INTERNET IS THINKING
Earlier sources: Language models
Language models learn patterns in text and other representations to predict or generate sequences. Follow model releases, training methods, reasoning, evaluation, and deployment research; a benchmark result is specific to its test conditions.
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 ↗447 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.
- OpenAlex · Published · First archived
Automating Injury Severity Score Calculation From Free-Text Discharge Diagnoses Using Domain-Specific Retrieval-Augmented Large Language Models: Retrospective Validation Study ↗
BACKGROUND: Trauma registries are crucial for evaluating the prognosis of injuries and the quality of trauma care. However, the calculation of Injury Severity Score (ISS) remains a predominantly manual process, which is labor-intensive, potentially error-prone, and difficult to scale. Automating this process is a critical step toward enhancing the efficiency and quality of trauma registry data. OBJECTIVE: This study conducts a feasibility test on the use of large language models (LLMs) to automatically calculate ISS from free-text discharge diagnoses. We specifically investigate the efficacy o…
- OpenAlex · Published · First archived
Bioacoustic raw-audio transformer effectively and efficiently encodes mixed sample rate data ↗
Abstract Deep learning has been widely adopted in the field of bioacoustics, enabling behavioral and ecological research into many sound producing animals through the use of specially designed and trained models. So-called foundational models can generalize to novel species or tasks, but require larger and more diverse training datasets. But the broad range of frequencies that animals produce poses a problem: bioacoustic datasets are recorded at various sample rates to capture different frequency ranges. Combining these data to train generalist models becomes exceedingly costly the wider the f…
- OpenAlex · Published · First archived
Weighted Proportional Conflict Redistribution for Heterogeneous LLM Ensembles ↗
Smaller language models often exhibit high confidence in erroneous predictions, undermining traditional ensemble methods. In heterogeneous ensembles, simple averaging can grant disproportionate influence to overconfident but incorrect outputs. This paper introduces a reliability-weighted extension of the Proportional Conflict Redistribution rule (PCR6), where model-specific weights are derived from validation accuracy. We provide a formal treatment of the conflict measure, prove that the weighted rule avoids Zadeh's paradox in the high-conflict regime, and establish a quasi-associativity bound…
- OpenAlex · Published · First archived
ClusSumm a user centered hierarchical clustering and adaptive transformer framework for efficient summarization of MOOC learner reviews ↗
Massive Open Online Courses (MOOCs) have become a major source of online education, generating large volumes of learner reviews that provide valuable insights into course quality and learning experiences. However, manually analyzing this feedback is time-consuming, while existing transformer-based summarization models often struggle to balance summary conciseness with information preservation. In addition, most evaluation frameworks rely solely on automatic metrics and rarely consider user preferences. To address these limitations, this study proposes ClusSumm, a user-centered hierarchical clu…
- OpenAlex · Published · First archived
Do large language models know which published articles have been retracted? ↗
Purpose Large Language Models (LLMs) can be helpful for literature search and summarization but retracted articles can confuse them. It is therefore important to know how aware LLMs are of retractions. Design/methodology/approach Three open-weight (offline) LLMs were asked whether 161 high-profile retracted articles had been retracted, with a similar check for a benchmark multidisciplinary set of 34,070 non-retracted articles. Findings From titles and abstracts, in over 80% of cases the LLMs claimed that a retracted article had not been retracted (GPT OSS 120 B: 82%; Gemma 3 27 B: 84%; DeepSee…
- Hugging Face · Model / dataset date · First archived
vincespeed/llm-runner-aio — model update ↗
# LLM Runner AIO v1.7 🌐 Links App Download Page: https://aihublocal.com/llm-runner-aio Community LLM Configurations: https://aihublocal.com/llm/configs Main Website: https://aihublocal.com 📋 Requirements * Node.js and Python 3.11 must be installed. * Optional Wan2GP video service: needs a few extra GB of disk space and the CUDA/driver version matching your GPU generation (exact requirements are shown in the setup confirmation window). * `LLM-Runner-AIO.exe` handles the automatic setup. * After extracting the `LLM-Runner-AIO.rar` files, you must run `run.bat` first; this script installs the n
- GitHub · Repository created · First archived
G36maid/moodle-mcp ↗
MCP server that lets AI agents operate Moodle: courses, assignments, forums, grades and files-as-markdown.
- GitHub · Repository created · First archived
glmn-ai/vibereceipt ↗
Print a store receipt for your AI coding: tokens, what they'd cost at API prices, and how many times the agent said "You're absolutely right". Claude Code, Codex, OpenCode. 100% local.
- Hacker News · Posted on Hacker News · First archived
Why Language Models Are So Hard to Understand ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: Boole-1.7B, a 1-bit LLM that outperforms Bonsai-1.7B ↗
Introducing Boole-1.7B, a 1-bit version of Qwen3-1.7B. Boole-1.7B retains 85.9% of BF16 performance using 247MB (13.9x smaller). It outperforms 1-bit Bonsai-1.7B and similar-sized LFM models, and nearly matches 1.58-bit Bonsai-1.7B. It’s intended for low-latency tasks using English and non-thinking mode. To learn more, - Blog: https://precisionnumerics.ai/blog/boole-1p7b - Weights: https://huggingface.co/precision-numerics/Boole-1.7B - Chat in br…
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about Language models
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.