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 ↗457 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
OpenStax-LLM: tools for OpenStax LLM access ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Rethinking LLM Serving with System One Models ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
From the creator of Redis; run LLM locally with ds4 ↗
Hacker News discussion.
- arXiv · Published · First archived
Decoding the Functional Roles of Register and High-Norm Patch Tokens in Vision Transformers ↗
Self-supervised Vision Transformers (ViTs), such as DINOv2, learn rich visual representations, but the functions of their internal tokens remain poorly understood. Recent architectures introduce dedicated register tokens to reduce high-norm out- lier patch tokens that emerge in background re- gions, yet the semantic and functional roles of both token types have not been fully established. In this paper, we analyze these roles by training sparse autoencoders (SAEs) on register-token and outlier-token activations in DINOv2. Using an automated interpretability pipeline, UMAP clus- tering, and CLI…
- arXiv · Published · First archived
Language Models that Play Chess and Explain Their Moves ↗
Modern chess engines are silent experts: they play at a superhuman level, but do not offer explanations for their play. On the other hand, language models (LMs) can generate plausible-sounding explanations, but their weak playing strength limits the utility of their explanations. We introduce Queen, a 4B-parameter chess-language model that can explain its moves and plans while playing at the level of a typical Grandmaster. Our novel framework enables domain-specific reasoning through complementary components: an encoder-decoder architecture and an iterative distillation algorithm. This archite…
- arXiv · Published · First archived
FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution ↗
LLM-guided evolutionary methods, such as AlphaEvolve, have emerged as powerful approaches for challenging computational optimization problems, such as circle packing. However, prior work typically optimizes performance gain over a fixed number of iterations. We argue that practical optimization should maximize gain per unit cost. To this end, we propose FrugalEvo, a cost-aware evolutionary framework where a stronger, higher-cost LLM explores solution strategies, and a cheaper LLM implements them and iteratively refines the resulting code. We also design a cache-efficient evolution process, whe…
- arXiv · Published · First archived
Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models ↗
Masked diffusion language models (dLMs) offer a promising parallel alternative to autoregressive models for complex reasoning. However, they face a distinct credit-assignment challenge, since a few commitments during denoising sharply reduce the uncertainty over the remaining masked positions and shape much of the response. Most post-training recipes for dLMs do not use this signal to decide which tokens to train on: they typically train on the final text or assign rewards to whole denoising steps, rather than selecting the individual commitments that shape the response. We introduce Pivot-SD,…
- arXiv · Published · First archived
Do Large Language Models Know Colombian Law? A Reliability Benchmark for the Colombian Legal System ↗
Large language models (LLMs) are increasingly used to support legal practice, education, and research, yet their reliability in national legal systems outside the United States remains largely undocumented. We introduce an expert-validated benchmark for evaluating LLM reliability on the Colombian legal system. The benchmark comprises 1,042 items spanning ten areas of law and three question formats (closed multiple-choice, semi-open, and open-ended IRAC), built through a human-in-the-loop pipeline with multi-stage expert review. We evaluate 15 contemporary proprietary and open-weight models wit…
- GitHub · Repository created · First archived
Aimee51819/FileFlipper ↗
FileFlipper — Quick Edit for Mac & Windows. One-click Markdown: turn Word, PDF, PowerPoint and Excel into clean Markdown that AI reads with fewer tokens. Plus Shift-drag conversion in Finder and File Explorer: JPG, PNG, PDF, HEIC, MP4, crop, OCR. 100% on-device, free and open source. Mac 和 Windows 都能用，一键转 Markdown。
- Hacker News · Posted on Hacker News · First archived
Show HN: One line so LLM workers share a 429 wait and keep jobs an outage stops ↗
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 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.