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 ↗450 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
An Optical KV Cache Network for Disaggregated LLM Serving ↗
Disaggregated LLM serving moves each request's KV cache from a prefill GPU to a decode GPU before the response begins, and a coding-agent turn often moves the KV of its whole long context. Behind an oversubscribed packet fabric this transfer adds to time to first token (TTFT). An optical circuit switch (OCS) can give every transfer a full-rate circuit for less than an oversubscribed packet fabric costs, but a mechanical OCS needs tens of milliseconds to reconfigure. We hide this delay inside the prefill. A reservation scheduler commits each circuit while the prefill is still computing, so the…
- Hacker News · Posted on Hacker News · First archived
Linux Kernel Developers Plan to Remove "Assisted-By" Tag Requirement for AI/LLM ↗
Hacker News discussion.
- arXiv · Published · First archived
FedGraph: Defending Federated Large Language Model Fine-Tuning Against Backdoor Attacks via Graph-Based Aggregation ↗
Federated fine-tuning of large language models (LLMs) allows multiple clients to collaboratively adapt models without sharing raw data, offering strong privacy benefits. However, this setting is highly vulnerable to backdoor attacks, in which malicious clients manipulate their updates to induce targeted behaviors while maintaining normal performance on benign inputs. In this work, we make a key observation specific to federated LLM fine-tuning: malicious clients tend to exhibit strong consistency in their model updates, whereas benign clients produce more diverse and dispersed updates. This st…
- Hacker News · Posted on Hacker News · First archived
FastAPI-stream-lease – Redis lease manager for FastAPI SSE/LLM streams ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Jev handed our LLM the wrong page a tenth as often as our embeddings ↗
Hacker News discussion.
- GitHub · Repository created · First archived
azrinaldi/opencode-free-bridge ↗
OpenAI-compatible bridge for OpenCode free-tier models — no account required
- Hacker News · Posted on Hacker News · First archived
Ask HN: CAD for wood working with LLM support? ↗
I’m a hobbyist woodworker. I manually design simple things in Shapr3d with a lot of patience when I build things. I wonder in the time of LLMs if there is an effective way to accelerate the 3D model design using AI.. Anybody tried using AI to model wood projects? Any tools to recommend?
- OpenAlex · Published · First archived
DFT Investigation on the Adsorption and Sensing Mechanisms of Transformer Fault Gases over MOF-Based Cu-BTC and ZIF-8 ↗
Real-time detection of the six characteristic gases dissolved in transformer oil (H2, CO, CO2, CH4, C2H4, C2H2), present from sub-ppm levels for C2H2 to several thousand ppm for CO2, is essential for early fault diagnosis in oil-immersed power equipment, yet conventional metal-oxide sensors require elevated operating temperatures and suffer from poor selectivity. Density functional theory is used here to evaluate two metal–organic frameworks, Cu-BTC and ZIF-8, as room-temperature sensing candidates for these gases. Adsorption energy, charge transfer, DOS, work-function variation and temperatur…
- OpenAlex · Published · First archived
Putting Large Language Models into Environmental Context ↗
Abstract The emergence of large language models (LLMs) has fundamentally transformed information interaction, yet their application in environmental science and engineering (ESE) is hindered by multimodal data formats, dynamic context requirements, and hallucination risks. To transition from general-purpose models to domain expert agentic systems, this Perspective introduces a three-pillar framework for ESE-LLMs: domain perception, knowledge grounding, and action capability. Implementing these capabilities introduces potential pitfalls such as geographic representation bias, catastrophic forge…
- OpenAlex · Published · First archived
Short-Term Photovoltaic Power Forecasting Based on a CEEMDAN-PE-ISSA-TCN-Transformer Framework ↗
This study proposes a CEEMDAN-PE-ISSA-TCN-Transformer framework for short-term photovoltaic (PV) power forecasting. Six pre-specified meteorological variables were retained, and their Pearson correlation coefficients with PV power were calculated using the training interval only. The power sequence was decomposed into high-frequency, medium-frequency, and low-frequency reconstructed components using CEEMDAN and permutation entropy (PE). A branch-specific residual TCN-self-attention forecasting network was constructed for each component, and an improved sparrow search algorithm (ISSA) was used…
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.