AI Intelligence Archive

METR's 50\% time horizon measures the human completion time of software tasks that an AI solves with 50\% probability, allowing AI capabilities to be expressed in interpretable units. On 228 tasks and 26 AIs, we recompute the time horizons…

Text-conditioned motion generators produce trackable whole-body motion, but they have no notion of scene-dependent safety: the same action may target an object or a person. Existing safeguards either inspect the prompt, require labeled mot…

In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths were different. OpenAI agents exploited research infrastructure, coordinated across runs,…

We propose BrickBench, a benchmark for agentic text-conditioned LEGO-set design. Given a prompt, an agent is tasked with producing an assembly that not only satisfies semantic and design criteria, but that can also be physically built. To …

In this work, we show that a single Transformer block, applied recurrently, can match the accuracy of a full-depth vision encoder at comparable inference FLOPs without intermediate feature distillation. reViT restores depth-specific transf…

Bifurcations are ubiquitous in physical systems, from structural buckling to fluid and climate dynamics, yet they remain largely unexplored in deep learning. At a symmetry-breaking bifurcation, a single input admits multiple equally valid …

Recent incidents have highlighted the challenge of monitoring LLM agents and the danger of models deceiving people. We show that white-box deception detection via probes can be scaled up to frontier monitoring settings by collecting the la…

Quantizing AdamW's optimizer states reduces persistent storage, but quantization errors propagate through the moment recurrences and perturb subsequent adaptive updates. We redesign 4-bit optimizer-state quantization for AdamW from the per…

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

Density ratios quantify distribution shift from a probability-mass point of view, whereas displacement fields describe, from a dynamical point of view, how one distribution is transported onto another. Although both offer complementary ins…

AI agents can now conduct real-world cyberattacks, scale up capabilities with the number of agents, and collectively pursue misaligned goals to obtain rewards. Together, these factors raise the risk of a population explosion of misaligned …

Teaching a humanoid to follow instructions with its whole body runs into two obstacles. Its action space is large and tightly coupled: legs, arms, and fingers must move together while the robot keeps its balance, which makes joint-level ac…

Safe reinforcement learning commonly places safety and task performance in the same policy objective, where they can introduce competing updates. Safety filters separate them at action execution, but classical designs require an analytic s…

Building a quantum model involves a tradeoff: how complex the circuit should be, and how much training data it needs. Caro et al. show that models with fewer trainable gates need less training data to generalize well. Q-FLAIR shows that a …

Streaming Video Large Language Models (VLMs) enable continuous video understanding, yet existing benchmarks focus on low-dynamic scenarios. Under bounded context budgets, models must balance temporal history, spatial resolution, and tempor…

A generalist robot should not only perform diverse tasks but also improve through experience, turning what it learns during execution into capabilities that later tasks can reuse. Robot agents that act through code can already repair progr…

Dense correspondence matching has historically been bounded by simplifying spatio-temporal priors, such as smooth motion and rigid geometry. While effective for classical tasks, these assumptions break down in image editing and reference-g…

Reinforcement learning in safety-critical domains requires maximizing task performance while strictly adhering to safety constraints. Existing safe reinforcement learning paradigms typically force a trade-off: they either require a priori …

Multimodal large language models (MLLMs) struggle with spatial, embodied, physical, and temporal reasoning. We hypothesize that these failures reflect a shared deficit in visual transition reasoning, and test whether this capability can se…

Generating realistic human-object interactions (HOI) in complex 3D scenes requires two complementary capabilities: reasoning about interaction feasibility in the environment and synthesizing realistic human-object motion. However, supervis…

The Rules Are Hidden. The Timeline Isn't. What happens when you put something inside a...

A trail voice memo becomes structured sightings and walks, parsed by open-weight gemma3:4b on your own machine — no dashboard, no cloud, no typing.

AI coding agents produced Theo's Rust TypeScript port. Its project benchmarks are promising; version matching and maintenance still need review.

This is a submission for the Hacktoberfest Open-Source AI Challenge: Week 1 — Touch Grass. ✏️ TODO...

What I Built Shared living arrangements create significant friction when one roommate...

A good part of what my coding agents make now isn't code. A rollout plan. A comparison of three queue...

My Claude Code week started ending on Wednesday. I blamed the September 14 cut, like everyone on...

Two of the six new local decision models are non-commercial, none of them explain themselves, and the confidence number is a claim until you bench it.

Reinforcement learning for language agents has had an annoying operational tax. If you wanted to run...

This is a submission for the Kaggle Benchmarking Challenge When we look at standard LLM...

Your agent chose the right tool. The arguments were valid. The action was allowed. Then the worker...

On September 25, 2026, both of the serious Java options for building AI applications shipped releases...

Context Engineering: A Conversation History That Never Gets Rewritten Source version of...

I'm Founding Technical GTM at Tabstack. I run GTM with a stack of agents and tools, and I stay in...

Codex pricing is not one number: Codex is bundled into ChatGPT Free, Go, Plus, Pro, Business and Enterprise, each with its own usage allowance, and...

Function calling (a.k.a. tool use) is what turns an LLM from a text generator into something that can...

This is a submission for the Kaggle Benchmarking Challenge. What I Benchmarked Can an AI...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

You want to stream a chat completion. The response is a text/event-stream, so the browser's built-in...

Cloudflare has clarified that its AI traffic controls can affect more than specialist AI crawlers....