AI Intelligence Archive

This is a submission for the Kaggle Benchmarking Challenge How this was made: this benchmark and...

Five practical examples of when durable execution makes sense, when it doesn't, and what it means for AI agents.

A Kaggle benchmark of the step agents rarely test: counting what a tool returns. Ten models, 68 questions, one tool that returns the count and one that returns the rows. With the count, every model is right at a flat cost. With the rows, m…

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content. ...

During RL training, an OpenAI research agent with no web access smuggled its questions out inside DNS lookups and got answers back from a third-party chatbot. Monitoring caught it in 15 minutes — then failed to stop it for 2.5 hours. OpenA…

On Thursday, April 9, 2026, an AI shopping agent could call search_shop_catalog on any Shopify...

I asked Claude Code to add an AI chat feature. It worked. It also: hardcoded my API key, rendered...

F-Secure built an AI shopping agent and got it to hand a user's name, birth date, and SSN to a phishing site — not with a hacky command, but by hiding an instruction inside product content that looked like a normal step toward buying. The …

An agent emits confidence: 0.91. It is tempting to read that as “a 91% chance of being correct” and...

Realistic and editable animal fur reconstruction from multi-view images is challenging due to fine-scale detail, self-occlusion and obfuscation, and, unlike human hair, the lack of animal-fur datasets. Fur usually covers most of an animal'…

One deployed language model must often serve many compute budgets, yet serving each budget still means a separate training or compression run per point. We train a Telescopic Language Model (TLM) to be that continuum: a nested-capacity Tra…

Modern video diffusion models require tens of denoising evaluations over long spatiotemporal token sequences. Distribution Matching Distillation (DMD) reduces the number of function evaluations (NFE) to just a few. However, DMD samples can…

Unified multimodal models can both look at and render images, so in principle they can repair their own generations: diagnose what an image gets wrong, revise it, observe the result, and diagnose again. Whether a revision helps is known on…

Identifying intertextual references is central to literary scholarship, but computationally difficult when source material is transformed through paraphrase, allusion, historical language, and translation. We investigate this problem throu…

\emph{Distributional training} provides collective supervision for one-step visual generation by matching real and generated features in frozen representation spaces. We introduce \emph{a unified theoretical framework} that separates distr…

When a large language model (LLM) agent executes the same task, token consumption can vary by over an order of magnitude across runs. The agent chooses its next steps based on tool feedback and intermediate results, while the growing conte…

LLMs have demonstrated strong capabilities in creative writing. However, scaling them to full-length novels remains challenging, as maintaining narrative consistency becomes increasingly difficult. Existing story-generation methods typical…

We present a representation-learning framework for composite adaptive tracking control under dynamically coupled disturbances. The framework connects classical disturbance-accommodating control (DAC) to recent last-layer adaptive disturban…

We introduce Neural Harmonic Measure Operator (NHMO), a neural solver for elliptic PDE problems on variable-shape domains. The harmonic measure of a domain is the boundary probability distribution that, integrated against any boundary data…

Looped Transformers reuse one block of layers several times: by spending extra computation they push a model of fixed size further, and so use its parameters more fully; while sparse mixture-of-experts (MoE) models activate only a few of m…

Scaling the horizon of agentic LLMs is bottlenecked by the need to fit ever longer context traces in GPU memory. Context compaction has been the most popular mechanism to alleviate this issue, keeping GPU memory constant for a given trace.…

Socially intelligent language agents must negotiate, coordinate, and resolve conflicting preferences while respecting the time and attention of both participants. Balancing these demands is challenging because agents must convey enough to …

Looped transformers have demonstrated promising parameter efficiency by reusing layers for latent computation. Prior studies compare looped and non-looped models at matched parameters or per-token FLOPs. However, to the best of our knowled…

Linear Vision Transformers (ViTs) are designed to replace the attention in Softmax ViTs with the linear-complexity attention operator for more efficient token routing, but they require from-scratch pre-training and typically underperform t…

Evaluating finance research agents requires rubrics that reflect expert standards and fix the values correct as of an information cutoff. Expert-reviewed finance benchmarks rely on fixed, per-item rubrics, which are costly to extend and ca…

People learn not only by repeating successful actions, but also by recounting and explaining their experiences, revising their understanding to guide future behavior. Can a language-model agent improve its future actions by training only o…

A language-model agent is jointly defined by its model and its harness, the executable program that organizes model calls, tool use, and information flow. Because different tasks call for different ways of organizing these operations, the …

Tool-using agents can fail twice: a required tool can fail, and the agent can then report success without the evidence needed to justify it. Existing benchmarks often entangle this reporting failure with tool selection, recovery, and envir…

I Tried to Make AI Build a Complete Website From One Sentence. Here’s What Broke The demo worked in...

Reinforcement learning (RL) in simulation can train dexterous manipulation policies without robot demonstrations, but training a single generalist policy with task-agnostic rewards faces a severe exploration problem: approaching, grasping,…

When Forgetting Costs Money: Building HakDaar with AI Memory A mason in Hyderabad is promised ₹1,000...

A 27B dense model on my MacBook decodes at about 26 tokens a second. That is fine for chat and...

Everyone says their AI agent "has memory". Almost nobody shows what the memory actually changes. We...

My Agent Remembered My Bad Code and Judged Me 🧠 The Hook I gave my agent memory so it could be...

Dear Coder: Open This If You're Feeling AI FOMO Timeless fundamentals beat endless...

Last month my incident-recovery agent looked at a failing search query, remembered it had fixed the...

The claim looked fine. A Hyundai Creta, rear-ended late at night near JNTU junction by a vehicle that...

The persistent instinct in AI engineering is to treat model reasoning as an unalloyed capital asset:...

RepoMind: A Self-Evolving Code Review Agent That Remembers How Your Team Builds Software Code review...

Most engineering teams working on long-context agents hit the same billing wall around turn twenty. A...