AI Intelligence Archive

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...

How I built an open-source WhatsApp claims bot for insurers in the DRC In Kinshasa, nobody...

Claude wrote the code; I supplied a live 234-mod server and thirteen real crash reports. Every bug was found by contact with reality, not by more reasoning. Here is each one.

Force-aware manipulation typically relies on specialized force or tactile sensors. We show that force-aware manipulation can instead be achieved through visual force prediction from the deformation of a compliant Fin Ray gripper. Our appro…

Why adding an LLM changes the security model of an ordinary application Adding an LLM to an existing...

Early-stage computational drug discovery requires coordinating heterogeneous scientific tools across multi-step workflows. We present a lightweight, tool-augmented framework in which a locally deployable compact language model plans calls …

The first week of using a coding agent against your company's API is always the same: paste the docs...

Reasoning models can remain capable of solving a task while still defaulting to cheaper but misleading shortcuts. This creates a central oversight problem: when a model gives an answer with plausible but incomplete reasoning, can an overse…

Structured prediction tasks pose unique challenges for in-context learning (ICL): their compositional outputs require modeling fine-grained, token-level patterns that sentence-level approaches fail to capture, and their task-specific annot…

A customer clicks Place Order. The spinner turns… and turns… then: Request timed out. So they click...

This work proposes a latent Lagrangian-based framework for reduced-order modelling of forced nonlinear dynamical systems. In contrast with conventional Lagrangian or Hamiltonian neural networks, our approach learns a set of latent coordina…

Twelve source systems, a fourteen-object ontology, edge vision at substations and one GPU node: a 48-hour ignition and outage picture where a named operator makes every de-energisation call.

Structural diagrams are widely used to represent complex systems and relational information across scientific, engineering, procedural, and spatial domains. Recent vision-language models (VLMs) have become increasingly capable of recognizi…

In a Transformer, token mixing is the step that lets each token draw information from other tokens, and it dominates the cost of encoding long sequences. Self-attention does this mixing very well: every token weighs every other token by co…

AI assistants receive requests that leave out information needed for a good outcome, for example about users' preferences or goals. They must then either speculate or ask for more information before proceeding. We reconceptualize this as a…

Logging code supports debugging, monitoring, and software maintenance, but excessive logging can add noise, impose runtime overhead, and obscure diagnostic information. While prior research has extensively studied logging code generation a…

We present GPU-accelerated Bregman Douglas--Rachford splitting algorithm (BDRS) for discrete optimal transport problem in three input formats: an explicit cost matrix, a point cloud with a ground cost between them, and a separable cost on …

Methods for assessing language-model agents include rule checkers over logs, analyses of skill coverage and composition, support checkers, prefix monitors, execution gates, and rare-event estimators. Each observes a different part of a run…

Operator learning methods such as DeepONets and FNOs often struggle with PDE families featuring sharp interfaces, heterogeneous coefficients, and localized multiscale structures. We introduce a partition-of-unity (POU) mixture-of-experts f…

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

People write and sketch while speaking to explain, organize, and develop content together. Inspired by these practices, we investigate how voice agents can use a canvas alongside speech in multi-turn conversations with users. We conducted …

Automated neurodevelopmental assessment increasingly combines computer vision, speech, eye tracking, physiology, and machine learning, yet multimodality and discrimination do not establish construct validity, clinical usefulness, or approp…

Recently proposed Drifting Models shift iterative distribution refinement from inference to training, enabling effective one-step generation. However, their performance on complex image datasets depends strongly on the representation used …

What I learned mentoring juniors for four decades seems to apply to today's agentic coding: why barking code fixes triggers sycophantic panic, and how Socratic questions yield 95%+ first-pass success.

A verifier for an agent faces rules of two kinds: the ones a fixed check can settle and the ones that require a judge. A team that derives its own checks fixes that split up front. Where the requirements come from outside, as in finance, h…

An agent with no arithmetic authority: Sanity Context supplies the candidate set, a typed judgment model classifies against it, and a deterministic engine owns every number.

Diffusion and flow models provide expressive policy classes for online reinforcement learning (RL), enabling multimodal behaviors and improved performance. However, training these policies remains challenging: the critic specifies the desi…

Operator eigenvalue problems appear throughout science. Classical methods usually discretize the operator into a matrix and then solve the resulting matrix eigenvalue problem. This works well in low dimensions, but fine grids quickly becom…

Agents are entering finance, healthcare and law, sectors where a violation leaves no lexical signature and carries real penalties. Whether an omission is material, or a disclosure sufficient, depends on what the response left out. Probing …

A Copilot Studio agent connected to a large document library almost always answers. The problem is...

Retrieval-Augmented Generation (RAG) is typically evaluated under the implicit assumption that the underlying knowledge base (KB) is clean, leaving the behaviour of RAG systems under realistic KB degradation poorly characterised. We introd…

Hello, I'm Maneshwar, and I'm building LiveReview — a blast-radius aware AI code review built for...

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I...

An agent submits a request to publish a document. The server commits it. The response disappears...

Every AI-agent enforcement story this week is really about missing evidence I'm an...

My own harness, the tooling I run around Claude Code, comes with a custom trust score. That trust...

Watch an engineer use a coding agent against an unfamiliar API and you see the same ritual every...

A friend messaged me lately: Where do you see IT going? Any new patterns in the post-AI era? My...

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

Originally published on mrsaynothing.dev — the receipts here get updated as the month rolls over,...