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.
- OpenAlex · Published · First archived
A review of deep learning transformer variants used in solar PV forecasting ↗
Abstract Solar power has become one of the most important renewable energy sources as it is sustainable, its prices are reducing, and it could contribute to the transition to clean energy across the world. Nevertheless, the inherently intermittent nature of solar PV output due to the rapidly fluctuating weather conditions demands a very serious need to have accurate forecasting systems. The current reviews are primarily over traditional deep learning or statistical models, creating a knowledge gap on how transformer-based architectures intend to separate long-term dependencies and nonlinear be…
- OpenAlex · Published · First archived
Behavioural biometrics-based continuous authentication using transformer networks for detecting insider-threat session hijacking ↗
Abstract Insider threats, in which a legitimate user’s already-authenticated session is taken over by another enrolled individual, evade one-time login authentication because the session is trusted before the takeover occurs. Continuous authentication, which re-verifies the user throughout a session from behavioural signals, is a natural defence. We study behavioural-biometric continuous authentication from keystroke dynamics and ask whether a Transformer network can detect insider session hijacking more reliably than established detectors. Using the public CMU keystroke-dynamics benchmark of…
- OpenAlex · Published · First archived
Benchmarking token mixers for efficient transformer-based learned video compression ↗
Learned video compression has rapidly evolved, with recent approaches demonstrating potential in complex context modeling. However, these performance gains often come at the cost of significant complexity in both framework design and computation-heavy modules, obscuring the efficiency contribution of the core architectural components. This work utilizes the video compression transformer (VCT) as a controlled testbed to isolate and quantify the contribution of the transformer-based entropy model by its core context modeling schemes. The authors propose an abstracted transformer entropy model (A…
- arXiv · Published · First archived
Trust Guided Decision Transformer ↗
Decision Transformer performance degrades on long rollouts because the conditioning context drifts out of the training distribution. We show that this drift is visible through the model's own next state prediction error, which rises during rollout and stays elevated, giving a direct signal of when context has become unreliable. We introduce Trust Guided Decision Transformer (TGDT), which selects context before applying value guidance. At each step, TGDT evaluates several recent context suffixes using rolling next state prediction error, calibrated against held out offline data via split confor…
- arXiv · Published · First archived
Configuration, Not Conscience: A Large-Scale Empirical Study of LLM System Prompts ↗
Leaked system prompts are often treated as windows into the hidden values of commercial language models, yet their composition is rarely studied at scale. We analyze a merged corpus of 407 leaked, reconstructed, or officially published system prompts from 62 vendors across four community collections, identifying 29 near-duplicate clusters covering 66 files. Operational content rather than ethical statements dominates the corpus; a deliberately simple block-level classifier assigns roughly 58\% of classified words to tool/protocol and roughly 5\% to safety policy, while the strictest rule-lines…
- arXiv · Published · First archived
EAServe: Encode-Aware Disaggregated Serving for Multimodal Large Language Models ↗
Disaggregating the two stages, Prefill and Decode, onto separate GPU pools is now a standard optimization for (text-only) LLM serving. However, multimodal LLMs (MLLMs), which add a third phase, Encode, pose new challenges for resource allocation. Encode turns images, video, or audio into embeddings that the language model can consume, yielding a three-stage Encode-Prefill-Decode (EPD) pipeline. Existing frameworks offer only partial answers: text-only PD systems lack Encode, while EPD frameworks expose it as a separate service without regulating downstream request flow. The pipeline also carri…
- Hacker News · Posted on Hacker News · First archived
Show HN: Reliopt – Pareto-frontier, contract-gated optimization for LLM programs ↗
Hacker News discussion.
- arXiv · Published · First archived
Can You Check That? The Checkability Boundary for Local LLM Network Automation ↗
Sending every network-automation input to a third-party frontier LLM exports sensitive artifacts such as production configurations, topologies, and logs. Querying small language models (SLMs) locally avoids this egress, but SLM outputs can be error-prone for direct use. This work introduces checkability as a criterion for determining which tasks are suitable for local inference. A task is checkable when it exposes a cheap, deterministic test - an intrinsic check - that rejects outputs violating a necessary correctness condition. We instantiate this idea in Touchstone, a local-first pipeline th…
- Hacker News · Posted on Hacker News · First archived
Prompt2ELF: An LLM wrote a 449-byte HTTP server without a compiler ↗
Hacker News discussion.
- arXiv · Published · First archived
Evaluating Cultural Awareness of LLMs for Haitian Creole ↗
Large language models (LLMs) exhibit substantial performance disparities between high- and low-resource languages. Beyond lower task performance, they often fail to capture the cultural norms and values of underrepresented communities. In this work, we present the first systematic evaluation of cultural awareness in LLMs for Haitian Creole, a language spoken by millions but severely underrepresented in digital resources. We assess cultural awareness along four complementary dimensions---specificity, bias, diversity, and variation---using a benchmark of culturally salient prompts curated by nat…
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.