THE INTERNET IS THINKING
Earlier sources: Artificial Intelligence
Artificial intelligence covers systems that learn from data, generate content, perceive their surroundings, or act toward a goal. Follow model research, agent tooling, evaluation, and the infrastructure used to build and run these systems.
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 ↗5496 classified signals in the fourteen-day window. Recent momentum: steady. 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.
- GitHub · Repository created · First archived
oztrkemree/mochi ↗
Mochi: a clay mascot for Claude Code that reacts to everything it does
- arXiv · Published · First archived
MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents ↗
A central challenge in embodied recursive self-improvement is enabling agents to convert interaction history into capabilities that persist beyond one world and transfer to later tasks. A saved memory or successful final action does not by itself establish that a reusable capability was acquired; evaluation must separate capability change from carried-over resources, unequal source exposure, and early execution failures. We construct MC-EvoBench as a controlled Minecraft benchmark with a fixed catalog of 19 registered evolution chains, including 12 primary evaluation chains and seven calibrati…
- arXiv · Published · First archived
OpenPA: Forced-alignment-free Multi-granular Pronunciation Assessment with Mixed-transcript Adaptation ↗
Recent advances in automatic pronunciation assessment (APA) have driven a shift from scripted to free-form assessment. However, existing methods often rely on multi-stage pipelines with forced alignment and separate feature extractors, limiting their practicality across response settings. In light of this, we propose OpenPA, a novel APA framework that leverages Whisper's cross-attention mechanism to jointly predict word- and utterance-level pronunciation scores without forced alignment. Through mixed-transcript adaptation and adaptive substitution weighting, OpenPA accommodates heterogeneous t…
- arXiv · Published · First archived
Same Query, Different Answer: Run-to-Run Variance in Semantic Query Processing ↗
Semantic query engines ask a large language model (LLM) to judge individual rows, and benchmarks compare these engines on the quality of a few executions at temperature 0. We measure how much another execution changes. We re-execute the text and tabular workloads of SemBench, LRO-Bench, and UDA-Bench through their own harnesses, log every one of 1.2 million model calls, and reanalyze SemBench's published executions. At temperature 0, between 0.07% and 10.2% of rows change their operator output over five executions, depending on the model, and up to 24.0% on one task. Plans amplify these change…
- Hacker News · Posted on Hacker News · First archived
Show HN: This hotel is hella AI-ready. Book directly from AI without MCPs ↗
Hey guys! Excited to show how we were able to get AI agents to read a hotel's live price and availabilities and even create the booking link to hand-off to the user. Get this, all working WITHOUT MCPs or connectors. All on the open web!!! Integrating with this system is possible under each hotel's domain too.
- 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…
- Hacker News · Posted on Hacker News · First archived
We gave an AI a phone and asked 1000 SF businesses a question ↗
We ran an experiment for SF Tech Week trying to understand how SF businesses are ready for AI. Very soon, every personal assistant like Muse, Instinct, Dots is going to call local places for us, so we wanted to understand what happens. Our AI called the businesses across different categories - vets, bars, cafes, dentists, hair salons etc. It was introducing itself as AI on every call and then asked a question which fits the business like “Are you…
- Hugging Face · Model / dataset date · First archived
francesca9805/ind-100mb-after-wc-uniform-newlex-before-ckpt500-packed-bfdiso_seed10 — model update ↗
# Model Card for ind-100mb-after-wc-uniform-newlex-before-ckpt500-packed-bfdiso_seed10 This model is a fine-tuned version of [francesca9805/ppt-wc-uniform-newlex-ind-before-100mb-packed-bfdiso_seed10](https://huggingface.co/francesca9805/ppt-wc-uniform-newlex-ind-before-100mb-packed-bfdiso_seed10). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-genera
- Hugging Face · Model / dataset date · First archived
drinnird/parakeet-tdt-0.6b-v3-sm8850-v81-fp16 — model update ↗
# NVIDIA Parakeet TDT 0.6B v3 - Qualcomm SM8850 NPU (FP16) **Device-specific Android deployment for WhisperRecorder v6.4** This repository contains a Qualcomm QNN / Hexagon HTP V81 deployment derived from [NVIDIA Parakeet TDT 0.6B v3](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3). It targets **Qualcomm SM8850, HTP V81, arm64-v8a**, with FP16-compiled neural contexts and an Android integration in **WhisperRecorder v6.4**. Unlike the original development-stage description, the Android application now implements a persistent **ONNX Runtime + QNN Execution Provider** transcription path for t
- arXiv · Published · First archived
MARGoS: A Configuration-Driven Platform for Reproducible MARL Experiments in ARGoS ↗
Multi-agent reinforcement learning (MARL) has become a prominent research direction, particularly within collective robotics, where the ARGoS simulator is widely used to study emergent swarm behavior. Yet despite this growth, systematic support for reuse and reproducibility in MARL-based swarm robotics remains limited and insufficiently standardized: a single experiment is assembled from manually aligned simulator files, training scripts, configuration values, paths, seeds, and environment details, so reuse and reproduction stay fragile even within one research group. To address this gap, we i…
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about Artificial Intelligence
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 ↗
Follow a thread
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.