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 ↗451 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
Your Transformer Is Secretly Elastic ↗
Scaling up transformers has produced models with broad capabilities, deployed across heterogeneous hardware and fluctuating workloads. Yet, model families offer only a few fixed sizes (e.g., S, B, L), forcing users to commit to a model based on hardware and latency constraints. This rigidity is often suboptimal under varying query loads. We introduce a retraining-free method that elastifies pre-trained transformers into a single model that adapts on-the-fly across a continuum of computational budgets. Our key contribution is a differentiable relaxation of the functional unit-ranking problem: u…
- arXiv · Published · First archived
Manacá-1B-Instruct-2: Reproducible Safety Alignment for a Native Brazilian-Portuguese LLM. Negative DPO Results, a Controlled Composition Scan, and a Silent Failure Mode of the LLM Judge ↗
Brazilian Portuguese remains underserved by open-source language models, and the few that are safety-aligned rarely document what did not work or validate comparisons with statistical significance. We present Manacá-1B-Instruct-2, the second-generation post-training alignment of Manacá-1B (1.72B parameters, trained from scratch for PT-BR), with an SFT corpus of 291,223 examples. We document three DPO attempts, all negative, including a case where the training reward margin reaches 1.0 while free generation does not change at all, and show that safety came from a dedicated safety-SFT (LLM-jp An…
- arXiv · Published · First archived
PerSo: Investigating Facets of LLMs' Social Intelligence in Real-World Persuasion Scenarios ↗
Understanding the social intelligence of large language models (LLMs) is increasingly important for applications involving human-AI interaction and multi-agent environments. Social intelligence comprises two aspects: cognitive intelligence, the ability to infer others' mental states, and behavioral intelligence, the ability to select appropriate social actions based on these inferences to achieve social goals. Persuasion provides a natural testbed in which both aspects are simultaneously at play, yet prior benchmarks typically evaluate them in isolation using synthetic scenarios. We introduce…
- Hacker News · Posted on Hacker News · First archived
Why do LLM pelicans look like this? ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: Eulix – Local code index and call graphs for large repos, LLM optional ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Specialty Steel Squeeze Drives EU Transformer Shortage ↗
Hacker News discussion.
- GitHub · Repository created · First archived
0xgetz/notion-bulk-9router ↗
Bulk-create Notion accounts and auto-wire each into 9Router as an OpenAI-compatible AI provider. Zero-dependency Node toolkit: disposable-email signup, automatic session/token/cookie extraction, and one-command 9Router registration.
- Hacker News · Posted on Hacker News · First archived
Adventures installing Prusa INDX with LLM help ↗
Hacker News discussion.
- arXiv · Published · First archived
LintEval: Benchmarking LLMs on Linter-Guided File Refactoring ↗
Linters are widely used in code maintenance and real-time IDE editing to surface lint alerts related to performance, style, error-prone, and other patterns in source files. However, existing code benchmarks do not explicitly evaluate linter-guided file refactoring, where models must reduce lint alerts in source files with correct initial functionality while satisfying functionality preservation. We introduce LintEval, a multilingual benchmark for linter-guided file refactoring across C++, Python, and Java, comprising 13,061 programs with correct initial functionality and 171,662 lint alerts ex…
- Hacker News · Posted on Hacker News · First archived
Show HN: Building an LLM from Scratch in TypeScript ↗
I wanted to understand transformers at a level where nothing is magic, so I'm building a ChatGPT-style model from first principles in TypeScript. Why not Python? I've found that reimplementing concepts in a different language forces me to grasp the nuance of the implementation. Chapters cover dataloaders, embeddings, and the attention mechanism so far. Feedback welcome if anything's unclear.
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.