AI Intelligence Archive

This paper introduces COUPLED FLOW, a new neural operator learning framework for multi-physics PDE systems that captures the co-evolution of multiple physical processes by modeling their cross-process interactions. Unlike existing neural o…

Data transformation pipelines shape the training distribution in computer vision, but designing them is a computationally expensive problem. We investigate whether large language models can enable efficient discovery by synthesizing execut…

The field of mechanistic interpretability is well-suited to collaborative projects between mathematicians and AI researchers. This work describes one such project. We trained a small transformer to learn the language of the Coxeter group a…

Independent rank-tracking data identified a significant Google results anomaly in September and...

Researchers increasingly estimate political behavior based on race and gender from voter files, where race is imputed from surnames and geography. This only works where surnames suggest group membership, an assumption violated where surnam…

Existing evaluations of AI models on high-finance work focus on retrieving answers from financial documents and producing numerically correct outputs. Real private equity (PE) and investment banking (IB) work also depends on choosing betwe…

Binary decision-making under uncertainty arises across a wide range of applications, including energy systems scheduling, transportation, and workforce planning. While machine learning has been increasingly applied to accelerate or replace…

In Bangla, a main verb is often followed by one of a small set of vector verbs. These verbs lose their own meaning and add a shade of meaning instead, such as completion. For example, likhe phello means that someone finished writing, not t…

Fixed prompt-based language models face challenges in open-domain conversations, where versatile topics require different expert advice or demonstrations to maximize their universal performance. Motivated by the dynamic prompt studies in l…

Detectors of AI-generated text are usually tuned and tested on passages of several hundred tokens, yet many real cases are short. We study score-based detection as a function of passage length. We give a closed form for how the false-posit…

Google can be prevented from fetching certain JavaScript resources during page rendering when those...

Real-world deployment of federated learning (FL) requires resilience against adversarial clients and data privacy. Byzantine fault captures the worst-case behavior of adversarial clients, while differential privacy (DP) provides statistica…

Standard ensemble methods can improve robustness by mitigating individual model stochasticity, but they frequently fail to generalize beyond the training distribution, leaving systems vulnerable to out-of-distribution (OOD) data. We introd…

Pre-training large parametric "Vision-Language-Action" (VLA) models on large demonstration datasets has recently yielded promising results for general-purpose manipulation. However, these models still struggle under even small domain shift…

Human-AI complementarity captures the idea that a human assisted by an AI system can outperform both the human and the AI acting alone. In prediction tasks, this improvement is assessed against ground truth labels produced through a refere…

Large Language Models (LLMs) exhibit approximate recall: they retain coarse associations about past events while losing fidelity on specific details. Past research on LLMs has quantified different models' forecasting ability in real-world …

Lighthouse 13.6.0 introduces changes to the simulation technology behind Lighthouse lab testing. That...

Much of the automation handed to language-model agents is procedural: each step needs little intelligence, but a long unattended run must follow a skill or SOP stated once at the start. We show that agents drift from such procedures over l…

Assessing climate risks requires projections of daily temperature distributions, including rare and spatially widespread extremes. Climate simulations are costly and biased, while correcting them toward observations risks suppressing inter…

Continual model merging incrementally integrates task-specific models without revisiting past models or data. However, repeated merging entangles past task components and distorts their singular geometry, making balanced task-wise allocati…

Big models are where inference engines show off. There's a lot of room to win. 27B is harder. The...

The New York Times has sued Brave Software, alleging that the browser and search company copied Times...

Submitted for the Flip the Switch Hackathon by WeMakeDevs & DevTools Academy (Powered by Switch...

357 seconds. That's how long the median request waited for its first token when we ran GLM-5.3 on...

Google, Microsoft and OpenAI have signaled support for a shared way for websites to express...

At 05:57 Eastern on November 6 my agent ran a scheduled self-audit. The audit handed it the correct...

The UK Competition and Markets Authority (CMA) has required Google to give publishers more detailed...

SMX Next 2026 is putting a clear strategic question in front of search marketers: how should organic...

I can't believe I'm saying this, but Ubuntu might be about to change for good. Not a new wallpaper...

A working paper examining ChatGPT’s international advertising rollout suggests that paid traffic from...

791 sellers advertise paid x402 endpoints. I called every route once and graded what came back. Here...

Building a human-gated incident team on Switch, with Claude Code agents working in Mattermost and...

Imagine being on call at 3 AM. An alert fires. A service is down, and logs are filling up with...

If you run Claude Code, Codex and OpenClaw on a Windows PC and want one app to chat with all of them,...

The message said: deployed, edge clean, no 5xx. Both of those things were true. The commit was on...

I kept getting drafts back from ChatGPT and Claude with the same habits. "It's not just a tool, it's...

Google is again drawing a clear line between preparing for AI-driven discovery and chasing isolated...

Answer: Nano Banana 2.1 is cheaper for iteration — 3 credits at 1K, 4 at 2K, 5 at 4K. GPT Image 2.5...

In mid-2024, 76% of pages cited by Google AI Overviews also ranked in Google's organic top 10 for the...

I shipped a Flutter app to production last year with an LLM chatbot baked in. Two weeks later a user...