AI Intelligence Archive

Introduction Cybersecurity is evolving rapidly. As technology advances, cyberattacks are also...

OpenAI counts reasoning tokens inside output_tokens, and Gemini counts thinking tokens separately. A short puzzle, the answer, and code you can run.

My first Solana program has one job: stand between an older parent and a scammer. Picture an older...

AI agents are moving from answering questions to doing things: sending email, sending contracts for...

@AnthropicAI - 排行榜：https://arcprize.org/leaderboard - 复现公开结果：https://github.com/arcprize/arc-agi-benchmarking - 测试政策：https://arcprize.org/policy - Claude Fable 5.2 完整结果：https://arcprize.org/results/anthropic-claude-fable-5-2

I'm building Finovaa, a budgeting app with an AI coach. It's launching on iOS and Android soon. The...

Machine learning models often achieve high average accuracy in the training data while performing poorly on test data due to subpopulation shift. A common data-centric solution is to enforce balanced subgroup proportions, but full balance …

Stochastic differential equations (SDEs) describe stochastic processes across a wide range of scientific domains, including physics, biology, and finance. Although individual numerical integration steps are inexpensive, observing meaningfu…

Motivated by reinforcement learning subject to communication constraints, we study a policy evaluation problem with linear function approximation over a rate-limited channel. In our setup, an agent interacting with an unknown environment (…

As multimodal agents accumulate increasingly long interaction histories, effectively retrieving and utilizing past information becomes critical for long-term interaction. Existing memory systems typically rely on semantic retrieval over co…

Anomaly detection (AD) is a critical for trustworthy machine learning and scientific discovery. Existing methods typically define anomalies through local density, isolation heuristics, or distance from a fitted distribution, making them se…

The Platonic Representation Hypothesis (PRH) suggests that neural networks are converging toward similar representation spaces. As language models become more capable, their representations are aligning with those of vision models. However…

Reinforcement learning (RL) can improve an agent's task capability while reinforcing behavior that violates contextual execution requirements. We study this reward-driven misalignment, including reward hacking, through verifiable reward--c…

Persona generalization occurs when fine-tuning a language model in one domain induces behavioral changes in others -- for example, the broadly unsafe behavior observed in emergent misalignment. We discover a surprising "on-the-line" phenom…

Large language model agents are increasingly deployed as multi-agent systems rather than as a standalone model operating within a single context. Recent agent harnesses allow the model to instantiate worker agents and to author the executa…

Latent Diffusion Models dominate generative modeling but face two-stage training complexity and the inherent reconstruction limits of pre-trained autoencoders. Pixel-space Flow Matching offers a simplified end-to-end alternative yet often …

As large language models become more capable agents, they can exhibit deceptive behaviors, cheating human for higher rewards while appearing helpful. We attribute this failure to evaluation-side partial observability, where models are eval…

AI models' growing capacity for complex reasoning has made them attractive tools for forecasting, or the systematic prediction of the future based on past and present data. However, should AI forecasting systems be adopted, human builders …

Low-precision pretraining is usually judged by validation loss. We ask whether matching loss also means learning rare facts as efficiently. We train transformers from scratch with emulated 4-bit matrix multiplications on synthetic biograph…

AI systems must often maintain bounded memory of unbounded interaction histories. However, optimizing the memory representation, and its updates, for downstream task utility is difficult for standard reinforcement learning (RL) due to seve…

One hundred known errors were planted into 10 open-access psychology papers, and the modified papers were then run through frontier models and two commercial AI review tools. The best single system caught 71 of the 100 errors, while the wo…

BACKGROUND: AI-based tools are expected to play a key role in lung cancer screening (LCS). The evaluation of these tools often relied on private datasets or fragmented public datasets with inconsistent availability of clinical data and exp…

The push towards circularity and Re-X principles presents a challenge to SMEs, particularly due to increasing product complexity that impedes the adoption of disassembly automation. This paper introduces and compares two frameworks for ext…

Counterfactual inference is the task of answering hypothetical "what-if" queries about a unit, given an observational dataset, modeling assumptions, and a causal graph. This enables a modeler to reason about hypothetical scenarios that can…

Users are asking language models mental health questions and are receiving answers. We audited what 41 language models recommend to users when the same clinical information reaches them from three footings: a clinician describing a patient…

The October failures behind my two-engine setup: Claude Code writes, Codex reviews read-only, and a script refuses merges without proof for the exact commit.

Dense non-rigid registration, the recovery of a pixel-wise deformation field that warps one image into geometric agreement with another, is fundamental across medical imaging, structural biology, and correspondence estimation, yet learning…

An agent is not just a chat window with better manners. It can call a model five times, search an...

Why I read them I'm building Folio Continuity, a shared project memory that AI agents read...

A 3,769-byte PDF whose visible page is a model card and whose /Keywords metadata carries a 1,579-byte SMS spam classifier.

There are two completely different AIs — the one you're forced to use and the one an expert chose — and we keep confusing them. Five measured findings, the methodology behind each, and the one mechanism that explains all of it.

With the Vega 2.0 launch last week, we have a bunch of new docs and videos for you, including guides to Hello World and OS compatibility, and videos on What's…

A month ago, an average web request on DEV took about 70 milliseconds inside Rails, with P99 response...

You head to the dog park with your dog Charlie on leash. You greet other dog owners there, and let...

Video world models conditioned on an input video make it possible to explore real, recorded dynamic scenes, enabling re-shooting of footage, free-viewpoint replay, and real-to-sim environments for embodied agents. Such uses require the gen…

We propose SciMARS, a framework for recursive task-local adaptation of multi-agent harnesses in closed-loop scientific discovery. Multi-agent systems coordinate analysis, experimental design, and verification as scientific evidence evolves…

We prove $F_{\mathrm{weighted}}(2,2,3) 0$ satisfies $\mathcal T_3\le(5/6-\varepsilon_0)E$ for every finite residual frame. The proof combines an exact scalar certificate, rigidity of equality in planar selection, and a compactness argument…

When you start learning Agentic AI, you quickly hit a wall. Most tutorials show you how to build a...

Alternating minimization is a standard tool for optimization problems with two coupled variable blocks. Its cost is dominated by the inner subproblem solvers, which rarely have a closed-form solution. In this paper, we propose to learn an …

What happens when the hardest-working user on your 16GB Mac and multi-cloud Ubuntu Dev-Box is a fleet of 20+ AI coding agents? Real benchmarks and fixes for 8s Chrome 136+ CDP hangs, 12GB APFS ghost clones, WindowServer freezes, and tmux r…