AI Intelligence Archive

Constructing accurate and computationally tractable approximation spaces is a fundamental task in scientific computing. Partially trainable neural networks bridge fixed random features and fully adaptive representations. This paper quantif…

We consider online monitoring of an AI system that produces a sequence of decisions. At each round, the system outputs a proposed decision together with a confidence score estimating the trustworthiness of the decision. The decision and co…

Auditing whether a text-to-image (T2I) model was fine-tuned on a particular image collection is difficult: a model can absorb collection-level visual characteristics without reproducing training images. Proactive dataset-use auditing plant…

Wrong automatic routing of an IT support ticket can cost more than human triage. We evaluate cost-aware abstention as an offline, cost-conditional readiness assessment: select a routing policy on calibration data under explicit costs, then…

Meta-reinforcement learning aims to train agents that adapt quickly to unseen tasks from limited interaction, but this requires representing task evidence over long interaction histories. Classical recurrent agents compress experience into…

Tool-using language model agents rely on environmental facts to decide whether an action is permitted. When a tool response omits a safety-relevant fact, an agent may carry out a prohibited action even though the user request is benign and…

Many recent open-weight language models use n-gram embedding tables to improve performance. These tables store learned representations of short token sequences, such as pairs or triples of consecutive tokens, which the model retrieves duri…

Standard implementations of softmax, log-softmax, and cross-entropy have two numerical bugs. The first bug, Softmax Collapse, rounds the target logit's gradient to zero if that one logit is much larger than the others, resulting in gradien…

Chain-of-thought (CoT) prompting elicits step-by-step rationales that appear to explain model predictions, but there is no guarantee these steps causally drive the final answer. In standard autoregressive generation, dense attention allows…

Multilingual pipelines such as FineWeb2 apply one recipe across a thousand languages, leaving the failure modes of individual languages unanticipated. We use an LLM once, as a corpus debugger rather than a classifier: a tool-using agent ex…

Looped architectures scale quality while keeping parameter count fixed by repeatedly passing activations through the same block of layers. During inference, each recurrence generates independent KV-caches, causing memory to grow linearly. …

Instrumental convergence is often invoked as a general reason to expect capable agents to acquire or express power-seeking subgoals: self-preservation, resource acquisition, deception, or resistance to oversight which poses an important th…

While monolingual language model (LM) surprisal is widely established as a predictor of reading times, it cannot capture the non-native (L2) reading dynamics that are shaped by the reader's first language (L1). In this work, we investigate…

On-policy distillation has been widely adopted for alleviating the distribution mismatch of off-policy distillation. Self-distillation further removes the need for an external teacher by using the student's own outputs, enhanced with extra…

We study learning a discrete distribution under person-level differential privacy in the batched setting. Given $n$ users, each contributing $m$ i.i.d. samples from an unknown distribution $μ$ over $[k]$, we seek an estimate of $μ$ with to…

Purpose: To describe an evidence-aware retrieval evaluation protocol for a clinical retrieval-augmented generation (RAG) system over breast lesion management literature, addressing the dependence of retrieval scores on annotation coverage.…

Google Gemini now provides two first-party ways to turn a natural-language prompt into a working web...

Counterfactual explanation methods have been introduced for unimodal settings, with dedicated frameworks for tabular, timeseries, text, and image data, yet no post-hoc method has been designed for classifiers that learn from multimodal inp…

Control evaluations measure whether safeguards can prevent an AI model from causing undesired outcomes even when it is intentionally trying to do so. These evaluations typically use purpose-built control settings and extrapolate their resu…

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

I was in Class 7 when I first properly touched a computer. My first lesson was simple: how to turn it...

Read this part first. I built a six-task benchmark that asks AI models to read auras, which they...

On 21 October 2026 PHP shipped an emergency release for two bugs in the language itself:...

A potential customer already knows your name. Someone they trust recommended your business. They...

Architect GKE for long-running Gemini 4 Argon agent sessions using VPA CPU startup boost, GCPBackendPolicy connection draining, and session checkpointing.

Day 22 of 30 Days of Search TL;DR To personalise and customize Valyu DeepResearch for a...

An enterprise AI governance stack is not a gateway feature. It is a sequence of decisions that has to...

We are thrilled to announce the winners of the Sanity Challenge, our partnership with Sanity built...

What founders report, what that evidence can't prove, and a four-week experiment you can run on your...

How I test AI-generated example sentences in a vocabulary app: invented words, a refusal that shipped as a card, a checklist that measured the wrong thing, and what the checks still miss.

If you have ever tried to write a long story with a general-purpose AI, you know the pattern. By...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

Two days ago I left a comment on Dimitris Kyrkos's post about agent retries ("Your agent's retry bug...

You want your coding agent to look something up in a web app. The app has a search box and an orders...

I asked my coding agent to merge a branch and clean up the worktree. It took 49 minutes. That's a...

Submission for the **Hacktoberfest Open-Source AI Challenge: Week 3 (Slow and Steady / Sloth...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady. ...

Everything starts with a small thought, what if I merge LLM & LLVM? Will I able to write...

A readiness assessment for AI teams moving agents from a prototype or another provider to Amazon...

This week two of our own help pages contradicted each other. MagicRemover's passersby page promised...