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 ↗429 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
Projected Primal–Dual Gradient Preference Optimization Under Category-Wise Split-Conformal Safety Constraints for Large Language Model Post-Training ↗
Preference optimisation improves helpfulness, but a single aggregate safety penalty lets frequent harm categories dominate the objective while rare ones bear the residual risk. This paper models post-training as a vector-constrained programme: the pairwise preference loss is minimised under one risk tolerance per harm category. The solver is a projected primal–dual gradient recursion that prices each category by its own residual violation. For a nonconvex objective we bound three horizon-averaged residuals—primal stationarity, dual regret and the average constraint value—for the unbiased, uncl…
- OpenAlex · Published · First archived
LLM Hallucination of Citations in Economics Persists With Web‐Enabled Models ↗
ABSTRACT Despite significant advances since 2023 in large language model (LLM) capabilities and the introduction of web‐enabled search functionality, citation hallucination remains a persistent problem in AI‐generated academic content. We test GPT‐4o, DeepSeek V3, web‐enabled GPT‐4o, and web‐enabled GPT‐5.1 across prompts derived from Journal of Economic Literature categories. Using a hierarchical citation validation framework, we find that even an advanced web‐enabled model produces non‐existent citations. While web‐enabled models show improvement over their predecessors, the error rates rema…
- OpenAlex · Published · First archived
PRECISE: Reducing the bias of LLM evaluations using prediction‐powered ranking estimation ↗
Abstract Evaluating the quality of search systems traditionally requires a significant number of human relevance annotations. In recent times, several systems have explored the usage of Large Language Models (LLMs) as automated judges for this task while their inherent biases prevent direct use for metric estimation. We present a statistical framework extending Prediction‐Powered Inference (PPI) (Angelopoulos, Duchi, and Zrnic 2024) that combines minimal human annotations with LLM judgments to produce reliable estimates of metrics which require sub‐instance annotations. Our method requires as…
- OpenAlex · Published · First archived
Attention-based foundation model for quantum states ↗
We present an attention-based foundation model architecture for learning and predicting quantum states across Hamiltonian parameters, system sizes, and physical systems. Using only basis configurations and physical parameters as inputs, our trained neural network is able to produce highly accurate ground state wavefunctions. For example, we build the phase diagram for the 2D square-lattice t t – V V model with N N particles, from only 18 training points in parameter space (V/t,N) ( V / t , N ) . Thus, our architecture provides a basis for building a universal foundation model for quantum matte…
- OpenAlex · Published · First archived
Emergence of polarization in networks of large language model agents ↗
Abstract Rapid advances in large language models (LLMs) have empowered autonomous agents to generate social networks, communicate, and form shared and diverging opinions on political issues. However, our understanding of their collective behaviours and underlying mechanisms remains incomplete. In this paper, we simulate networked systems involving thousands of LLM agents across different backbone models (GPT-3.5, GPT-4o, ChatGLM, Llama-3, and DeepSeek-V3), in which agents interact through LLM-guided conversations and update their opinions over time, resulting in the emergence of opinion polari…
- GitHub · Repository created · First archived
krxi/asmsense ↗
asmsense: a small model that names and describes functions in stripped x86-64 binaries. Open dataset, baselines, and LoRA experiments.
- GitHub · Repository created · First archived
0xcro3dile/answerui ↗
Open-source alternative to ChatGPT's Intelligent UI. Answers arrive as live charts, forms and calculators. Works with any OpenAI-compatible model, in the cloud or local.
- GitHub · Repository created · First archived
MicroZ-LLC/AllInOneIME ↗
A macOS input method with AI commands in every text field: @improve polishes, @translate translates, @question answers, @claude hands off to Claude Code. Also a full pinyin input method.
- GitHub · Repository created · First archived
bing-xu-graphics/light_transformer ↗
Open-source repository in Python.
- Hacker News · Posted on Hacker News · First archived
I'm not paying $20 for ChatGPT or Claude because a free local LLM does ↗
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.