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.
- arXiv · Published · First archived
Benchmarking Attention for Tabular Foundation Models ↗
Tabular in-context learners such as TabPFN, Mitra, or ConTextTab rely on alternating row and column attention over 2D sequences of latent embeddings. These attention patterns differ markedly from the one-dimensional case in language models: row attention involves longer sequences while column attention operates on much shorter ones, and the strided memory layout of tabular data makes producing contiguous tensors costly. Moreover, the hidden dimensions used in current models are small compared to recent language models. Yet efficient attention has been studied mostly for one-dimensional sequenc…
- arXiv · Published · First archived
When the Model Retires: An Empirical Study of LLM Migration in Open-Source Applications ↗
Applications built on commercial large language model (LLM) APIs depend on model versions that providers retire on their own schedule, with notice periods ranging from one year to two weeks. We ask what actually happens to applications when a model is retired. We mine GitHub for commits that migrate away from officially deprecated models and endpoints of OpenAI, Anthropic, and Google, matching each commit to the provider's published announcement and shutdown dates. From 22,555 commits in 17,703 non-fork repositories (2024-2026), 5,139 are matched to an official event; two independent coders va…
- Hacker News · Posted on Hacker News · First archived
A Jevlike using an escalation model to route between a classifier and an LLM ↗
Hacker News discussion.
- GitHub · Repository created · First archived
FeiLiuEM/open-medical-jev ↗
High-performance, high-precision, locally-deployed Jev-class medical decision service on national medical exams — four readings, one routed decision, zero training.
- arXiv · Published · First archived
RupeeBias: Auditing Demographic Bias in Indian Economic Guidance from Large Language Models ↗
Individuals turn to large language models (LLMs) for guidance across a wide range of economic tasks, from comparing loan options and planning savings to deciding what raise to ask for or how much to charge for their services. LLMs are known to reproduce social biases, and biased economic guidance may influence what users believe they are worth, what they ask for, and what they ultimately accept. This risk is especially salient in India, where economic outcomes are shaped by demographic categories such as caste and urban-rural location. Existing LLM bias benchmarks, however, are largely designe…
- Hacker News · Posted on Hacker News · First archived
Ask HN: How do you use LLMs to secure your code and services? ↗
Do you just download random skills? Write your own prompts? Pay for a specialized service? Or just OAI and Anthropic? Use open source software (which)?
- Hacker News · Posted on Hacker News · First archived
Show HN: LabLoop – isolated infrastructure for LLM-driven scientific experiments ↗
Hacker News discussion.
- GitHub · Repository created · First archived
Morrowmake/glm53-flash-cmp170hx-recipe ↗
GLM-5.3-Flash on 4× NVIDIA CMP 170HX with vLLM: 264 tok/s single-user, 763 tok/s at 8 users, 262K context, TP4 or PP4, one-command container install
- GitHub · Repository created · First archived
Xuanwo/cida ↗
辞达：用你选择的大模型，在 Mac 的任何地方翻译和润色文字。Translate and polish text anywhere on your Mac.
- Hacker News · Posted on Hacker News · First archived
Your Language Model Is Already a Decision Model ↗
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.