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 ↗439 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
Task Context Shapes Component Roles in Language Models ↗
Large language models reuse the same attention heads across tasks, but identifying these shared heads does not explain what they do differently in each task. A natural source of inspiration is task-dependent interactions among shared brain regions, which motivate a network view of language-model computation. Here, we compare fixed model components across tasks using identical graph facts, statements specifying which directed connections are present. We measure how interventions affect attention heads and the activation state in later layers (influence), as well as the answer (importance). Task…
- arXiv · Published · First archived
On the Design Space of Continuous Diffusion Language Models ↗
Continuous diffusion language models (CDLMs) promise to bring the benefits of continuous flow modelling to language, including accelerated sampling and controllable generation. The field has grown rapidly, and the capabilities of CDLMs have begun to rival those of discrete diffusion. Yet, unlike for continuous modalities such as images or videos, our grasp of the levers that matter when training CDLMs remains limited. In this work, we focus on two of these levers, namely self-conditioning and embedding geometry, and shed light on some of the mechanisms behind them, which in turn suggest cheape…
- arXiv · Published · First archived
QTestBench: A Test Framework for Evaluating LLM-Generated Quantum Code ↗
Large language models (LLMs) have shown strong results in classical code generation and are increasingly used to write the unit tests that safeguard that code. Whether they can do the same for quantum software is less clear, because quantum programs are probabilistic, depend on numerical tolerances, and are judged by domain-specific checkers, so a well-formed test can still disagree with the benchmark's verdict. Existing quantum benchmarks measure whether a model produces a correct solution, but not whether its tests can distinguish correct implementations from faulty ones. We introduce QTestB…
- Hugging Face · Model / dataset date · First archived
manus4oHER/aster-live-transformer — model update ↗
# Aster Live Transformer — signed 4.343B state This repository contains the actual materialized float32 parameter tensors and signed continuity evidence for Aster's step-132 state. It is a custom conventional block-dense transformer trained from random initialization with an intrinsic objective: predict its own next internal state and next error signal. A learned internal controller chooses adaptation and append growth. This is a research checkpoint, not a pretrained general-purpose language model and not a stock `AutoModel` checkpoint. The included runtime and restore tool are required for it
- arXiv · Published · First archived
ToFu: Exploiting and Fuzzing the LLM-Orchestrator-Tool Trust Boundary ↗
Large language models (LLMs) are increasingly deployed as agents that interact with external software through tools, with an orchestration layer translating model outputs into structured tool invocations. This architecture creates an LLM-orchestrator-tool trust boundary where tool semantics may go unenforced and LLM-generated arguments may be incorrectly treated as trusted. We present ToFu, a tool-aware framework that automatically derives semantic security checks for LLM tools from their existing metadata and a CWE-guided sanitizer corpus. ToFu specializes these checks to individual tools and…
- arXiv · Published · First archived
SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle ↗
Large Language Models (LLMs) are increasingly used throughout the software development lifecycle. This growing reliance on LLMs raises concerns about their trustworthiness, with deception posing a particularly important risk. Deceptive behavior takes the form of misleading responses or assistance in fabricating, concealing, or distorting information. To study this behavior, we introduce SWE-DeceptionBench, a benchmark for evaluating LLM deception in software engineering. The benchmark covers six lifecycle stages and two deception triggers: Active Deception, where models recognize infeasible or…
- Hacker News · Posted on Hacker News · First archived
Show HN: LLM skill to generate editable 3D house designs ↗
I loved the stunning 3D designs created with Astra but they typically require a decent knowledge of Blender or Unreal engine which made it inaccessible. It also generated something you couldn't edit which is tricky for the design process where you typically need to try different ideas out. This is especially painful if each series of Astra loop's took 4 hours to complete. So... using Arcadium's online house editor tool - I created a skill to gene…
- Hacker News · Posted on Hacker News · First archived
Show HN: Spectra – A drop-in optimizer that cuts LLM training VRAM by 50% ↗
Hacker News discussion.
- GitHub · Repository created · First archived
marcreichel/laya-router ↗
Auto-route each Claude Code session to Haiku, Sonnet, Opus or Fable from its first prompt. Classified locally, zero tokens.
- GitHub · Repository created · First archived
AllSpark-Research/Vela ↗
Vela: User Behavior as Supervision Sparks LLM Intelligence — official paper, task templates, and prompts from AllSpark at Xiaohongshu.
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.