THE INTERNET IS THINKING
Earlier sources: AI infrastructure
AI infrastructure comprises the compute, storage, serving systems, and operational tools used to train and deploy models. Follow inference engines, distributed training, observability, and the costs and constraints of running AI workloads.
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 ↗41 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
Thinking Outside the Box: Retention and Transmission of Information in Sliding-Window KV Inference ↗
Sliding-window KV inference refers to processing a sequence incrementally while retaining only a fixed-size cache of recent key and value states. It can be applied to pretrained causal transformers at inference time without additional training, while its KV-cache memory remains fixed as more tokens are processed. Because cached states are computed in the context of earlier tokens, they may carry information from beyond the current window and transmit it to later states. This study presents a series of experiments using five open-weight models spanning Qwen, Llama, Mistral, and Muse Glimmer. We…
- arXiv · Published · First archived
Singularities of Non-negative Matrix Factorization and their application to Bayesian inference ↗
Non-negative matrix factorization (NMF) is a singular statistical model whose Bayesian asymptotics are governed by the real log canonical threshold (RLCT). We study the local geometry of the factorization map and derive an upper bound for the RLCT of NMF. Let $H$ be the model inner dimension and $H_0$ the non-negative rank of the true $M\times N$ matrix. Assuming that the true matrix admits a strictly positive factorization of inner dimension $H_0$ in the interior of the parameter domain, we prove, for smooth positive priors, that $λ\leq \{(H-H_0)\min(M,N)+H_0(M+N-H_0)\}/2$. This bound strictl…
- arXiv · Published · First archived
Posterior Regimes and Latent Deception: Variational Bayesian Inference in Hidden Markov Models for Sequential Fraud Detection in Financial Transactions ↗
We present a three-tier progression of Hidden Markov Models: maximum-likelihood (Baum-Welch), variational Bayesian (VBEM), and a neural variational extension (Neural VBEM), that model each customer's transaction history as a trajectory through a small number of latent behavioural regimes, one of which is empirically identified as fraud-associated. The Neural VBEM HMM replaces the fixed Gaussian-multinomial emission family with a learned encoder, compressing a 741-dimensional transaction representation into a 64-dimensional latent space in which the VBEM HMM's posterior operates; a UMAP project…
- Hacker News · Posted on Hacker News · First archived
Ask HN: How are you getting inference for personal projects? ↗
It seems like the major providers are starting to cut back the usage included with their monthly subscriptions. How are people handling inference for side projects these days? Are you still using Codex/Claude subscriptions, paying for hosted open weight models, running local models, etc
- OpenAlex · Published · First archived
RF-SPEA2 Hybrid Rule Inference and Optimization Architecture ↗
The high predictive performance of machine learning models in complex classification tasks often comes with limited transparency, particularly for black-box models whose decision processes cannot be directly inspected. In this study, a two-stage Random Forest–SPEA2 hybrid rule inference and optimization architecture is proposed to achieve high predictive performance while retaining an explicit rule-based decision structure. In the first stage, root-to-leaf decision paths extracted from Random Forest trees are converted into interval-based IF–THEN rules, and a class-balanced candidate rule pool…
- arXiv · Published · First archived
Reading Is Not Leaking: Local, Auditable Measurement and Reduction of Inference Exposure from Public Footprints ↗
Anyone with a public footprint leaks facts that were never stated, and language models make the inference cheap. We present a framework for measuring and reducing this inference exposure that runs on the owner's own CPU with no language model at analysis time, instantiated on organisations and on individuals. It starts from a measurement result: scoring an inference system against the target's private truth conflates how well the system reads the record with how much the record leaks. On a 128-question instrument over sixteen synthetic firms, almost half of the questions are never answered cor…
- GitHub · Repository created · First archived
publicExcess/splish ↗
Splish: an unofficial fork of Inco's Splash, tuned for Apple M5 GPUs. Up to 1.5x faster (about 1.25x at one request) on Qwen3.8-27B. Apache-2.0
- GitHub · Repository created · First archived
Abhinivesh2729/Thinai ↗
Thinai is a privacy-focused Android app that runs small language models locally on your device, with a local API for integrating and accessing on-device AI inference.
- GitHub · Repository created · First archived
ArtificialAnalysis/aa-agentperf-local ↗
Benchmark local LLM serving by replaying real agent trajectories
- GitHub · Repository created · First archived
Verzeta/Verzeta-Studio ↗
Open-source, local-first AI team workspace. Several AI models work together in one conversation, each with its own provider, model and tool whitelist. Android and VS Code clients pair in. No telemetry.
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about AI infrastructure
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.