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 ↗459 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.
- Hacker News · Posted on Hacker News · First archived
What is LLM-as-a-Judge, and How It Works? ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: SelMem – selective reconstructive memory for LLMs ↗
A project which explores whether LLM agents can develop persistent behavioural divergence through a reconstructive memory system that forgets, distorts, and consolidates experiences over time.
- Hacker News · Posted on Hacker News · First archived
OpenAI and Microsoft Admits LLMs Are Destroying the Web and Built on Theft ↗
Hacker News discussion.
- GitHub · Repository created · First archived
ntlm1686/Your-language-model-is-already-a-decision-model ↗
We compared unfinetuned Qwen with Jev on decision accuracy, calibration, and latency, and found comparable accuracy and lower average calibration error without decision-specific fine-tuning.
- OpenAlex · Published · First archived
Reservoir Modeling Assisted with Knowledge-Enhanced Large Language Models ↗
Reservoir simulation is an important technique to characterize subsurface fluid flow and to support reservoir development and production optimization. Conventional reservoir modeling requires engineers to extract model-relevant information from heterogeneous data, organize the information into predefined formats, and generate simulator-specific input files through professional software. Constructing and iteratively updating such models can often take months of effort due to the high modeling complexity. Large language models (LLMs) offer a potential alternative by translating modeling requirem…
- OpenAlex · Published · First archived
Beyond Accuracy: Evaluating Evidence Grounding in Multimodal Large Language Models for Newspaper Understanding ↗
Although multimodal Large Language Models (LLMs) perform well on document question answering tasks, Answer Correctness, i.e., whether a model’s answer is correct with respect to the question, does not fully describe model behavior because it does not show whether answers are supported by relevant evidence. This paper presents a framework for multimodal document understanding that jointly evaluates Answer Correctness and Evidence Grounding, i.e., whether the evidence cited by the model alongside its answer is present, relevant and consistent with that answer. We evaluate two LLMs on an initial…
- OpenAlex · Published · First archived
LLM-H2G: biomedical semantic-enhanced hypergraph contrastive learning for herb–disease association prediction ↗
Abstract Background Herb–disease association prediction is central to computational traditional medicine, but existing graph and hypergraph methods mainly rely on observed topology and underuse biomedical textual semantics, especially in heterogeneous or sparse association networks. Results We propose LLM-H2G, a biomedical semantic-enhanced hypergraph contrastive learning framework that integrates herbs, compounds, proteins and diseases through an enhanced heterogeneous hypergraph. Entity names are encoded as large language model-derived semantic representations, injected into compound and pro…
- OpenAlex · Published · First archived
Multi-domain feature fusion and machine learning-based SFRA diagnosis of transformer winding faults using a novel fault deviation index ↗
Abstract Sweep Frequency Response Analysis (SFRA) is one of the commonly used techniques for evaluating transformer winding integrity. However, the interpretation of the SFRA results remains qualitative and depends on expert evaluation. In this study, a quantitative, measurement-oriented diagnostic framework based on the advanced normalized Multi-Domain Fault Deviation Index (MFDI) is proposed. Within this method, magnitude, phase, impedance, and resonance-based descriptors are integrated in a unified formulation. The proposed method combines frequency band decomposition with multi-domain feat…
- OpenAlex · Published · First archived
From capability to assertability: epistemic regulation of LLM-mediated claim presentation ↗
Abstract Improvements in large language model (LLM) capability can increase accuracy, reasoning, and access to relevant information while leaving unassessed whether a particular output is appropriately presented for epistemic uptake. This creates an evaluative gap: first-order capability metrics can register genuine gains while leaving claim-presentation conditions underdetermined. LLM outputs increasingly occupy assertion-like roles without thereby acquiring the standing of accountable asserters. We develop assertability as a relational normative status of an output-in-practice, determined by…
- OpenAlex · Published · First archived
Nutritional Accuracy and Clinical Applicability of Large Language Model-Generated Therapeutic Diet Plans for Phenylketonuria: A Comparative Simulation Study ↗
Background: Large language models (LLMs) are increasingly used to generate nutrition-related recommendations, but their reliability for therapeutic diets requiring precise nutrient control remains uncertain. This study evaluated AI-generated one-day diet plans for standardized simulated cases of classical phenylketonuria (PKU). Methods: Eight standardized simulated cases representing infancy, adolescence, adulthood, and maternal PKU were evaluated. Between 8 and 10 February 2026, ChatGPT-5.2, Claude 4.5, and Gemini 3 were each used through their standard consumer-facing chat interfaces to gene…
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.