Time Capsule of Testable Human Knowledge: 41 Years of Jeopardy! in a Single Free Local Model
arXiv:2608.27459v1 Announce Type: new
Abstract: In 2011, IBM's Watson was something like a sealed capsule of its era's queryable knowledge. Its DeepQA system defeated the strongest human Jeopardy! champions, but the knowledge that let it do so lived in a curated billion-document corpus running on a...
Rating the Raters: Rasch Measurement Theory for LLM Evaluation
arXiv:2608.27463v1 Announce Type: new
Abstract: LLMs now sit on every side of evaluation: as examinees scored on benchmarks, judges of other models' outputs, and raters of human-generated content. Each paradigm can be viewed as a measurement problem, where a latent property of an object is probed w...
Not All Explanations Are Sought: Information-Seeking Psychology for Human-Centered XAI
arXiv:2608.27464v1 Announce Type: new
Abstract: This position paper argues that human-centered explainable AI (HCXAI) should incorporate insights from the psychology of information seeking. Drawing on Sharot and Sunstein's framework of information-seeking motives, we propose that people evaluate wh...
Retrieving Relations, Detecting Fallacies: A RAG Approach to Political Debate Analysis
arXiv:2608.27471v1 Announce Type: new
Abstract: Fallacies are arguments that employ invalid reasoning, making their automatic detection critical in sensitive contexts such as high-stakes political debates, where public opinion is shaped. Spotting a fallacious argument requires contextual knowledge ...
LLM-Augmented Causal Discovery: Probabilistic Fusion of Edge Existence and Orientation
arXiv:2608.27472v1 Announce Type: new
Abstract: Bayesian network structure learning (BNSL) from observational data struggles with orientation identifiability, while large language models (LLMs) offer broad but often unreliable causal knowledge. We propose combining these complementary sources throu...
Lowest-Latency Inference APIs for Voice and Realtime Agents: A Time to First Token TTFT-First Benchmark
Voice agents fail on latency long before they fail on intelligence. Time to first token is the metric most teams use to choose an inference API, and it is the right starting point and the wrong stopping point. This benchmark works through every layer of the voice stack — LLM, speech-to-text, text-to...
Google AI Introduces EnvHarness: A Programmable Layer That Turns Static Agent Environments Into Adaptive Training Worlds
Google Cloud AI Research, with Washington University in St. Louis and UNC Chapel Hill, has released EnvHarness, an Apache-2.0 layer that turns a static agent benchmark into one that adapts to the policy training on it. It wraps a frozen environment through the standard reset()/step() interface, so t...
Top 7 Free AI Automation Courses with Certificates
You don’t need to know anything about AI automation to get started. There are plenty of free courses that can take you from the basics to building your own automations, even if you’re starting from zero. Some are completely beginner-friendly, while others are better once you’re comfortable with the ...
Quick and simple tips to help you write better agent instructions
The post 8 Tips for Writing Effective Agent Instructions appeared first on Towards Data Science.
Musk’s faster path to more gas turbines comes with pollution problem
Elon Musk says a secretive new SpaceX foundry will let him cast his own turbine blades and get gas power online 18 months faster than anyone else — but it's a bet on a fuel source that's already triggering lawsuits and health studies everywhere his (and others') turbines have gone in.
Context Engineering Is Changing. Here’s What It Means for Data Scientists
How to apply the latest context engineering guidelines to your day-to-day data science work
The post Context Engineering Is Changing. Here’s What It Means for Data Scientists appeared first on Towards Data Science.
Meet ‘Code-as-World’: An Agentic Loop That Rewrites Real Videos Into Executable MuJoCo Physics Programs
Code-as-World recovers editable MuJoCo scene code from real video, then uses those verified worlds to train physical reasoning.
The post Meet ‘Code-as-World’: An Agentic Loop That Rewrites Real Videos Into Executable MuJoCo Physics Programs appeared first on MarkTechPost.
AI Weekly Issue #527: Schools are choosing opposite futures for AI
One University of Chicago curriculum is removing AI-assisted writing from the classroom. Alpha School is expanding a model that puts adaptive software at the center of the academic day. The strongest signal in the latest Who’s Who Global Edition is that education is moving past general principles an...
Building Custom Batched Ensemble Weather Forecasting with NVIDIA Earth2Studio
In this tutorial, we build an ensemble weather forecasting workflow with NVIDIA Earth2Studio. We install the required Earth2Studio components while preserving Colab’s existing CUDA-enabled PyTorch environment, load the FCN prognostic model, and retrieve atmospheric initial conditions from GFS. We th...
“We’re not doing 30 bets a year”: Vijay Pande on betting small after running $4 billion at a16z
Vijay Pande — who left a16z's roughly $4 billion biotech practice last year to start the much smaller, AI-native VZVC — talks about why biology is finally shifting from a "discovery" science to an "engineering" one, why clinical trials are still brutally expensive, and why he thinks open, shared dat...
Google AI Releases Gemini Omni 1.1 Flash: 40-Second Scene Extension, First/Last Frame Control, and 4K Upscaling
We look at Gemini Omni 1.1 Flash, Google's production update to its native multimodal video generation and editing model. We break down what changed: scene extension now reads up to 10 seconds of prior context instead of a single final frame, first and last frames can be pinned to control camera mov...
RAG Is Not the Whole Toolkit: The NLP Techniques Real Problems Still Need
Enterprise Document Intelligence [Vol.1 #B00] - Retrieval answers one kind of question. Classifying a request, matching free text to a reference list, reading a table, cleaning OCR noise: each has a cheaper method that works, and the engineering is knowing which one to reach for
The post RAG Is Not ...
Hugging Face Unveils Microduck: A $399 Open-Source 25 cm Biped You Train with Reinforcement Learning
Pollen Robotics, the Bordeaux robotics team at Hugging Face, opened pre-orders for Microduck — a 25 cm bipedal robot where every movement is a neural policy trained in MuJoCo and exported to ONNX. At $399, it puts the full sim-to-real loop on a desk: 15 motors, camera, LiDAR, two IMUs, and an Apache...
How we stopped reviewing every agent action and started routing human attention where it actually mattered
The post Human-in-the-Loop Without Killing Throughput appeared first on Towards Data Science.
Vercel AI Open-Sources vgpu: A TypeScript WebGPU Library for AI Agent Shaders
Vercel has open-sourced vgpu, the WebGPU library it built to ship the shaders on vercel.com. It treats .wgsl files as importable TypeScript modules, runs the same shader in the browser, in headless Node.js via Dawn, and in a deterministic CI mock, and ships a fullscreen effect in 25 KB gzipped.
The ...