AI Intelligence Archive

Extreme weather is forecast days ahead, yet its consequences for agriculture remain hard to predict: a forecast says where a storm will strike, not which crops will suffer or how much is at risk, and the records that could tell span many s…

World models can achieve strong control performance without faithfully capturing the dynamics of their environment, limiting their potential for mechanistic interpretability and scientific discovery. Here, we introduce world2vec to learn m…

An observer sees only part of the surrounding world, yet must keep track of what lies beyond the current view. Spatial perception therefore involves more than recognizing individual images: it calls for a persistent spatial state that is u…

You do not need a live LLM to reproduce most bugs in an AI chat interface. These failures are...

Safety alignment has enabled large language models to reliably refuse harmful requests directly, yet the same request distributed across a multi-turn conversation still succeeds far too often. This brittleness has a mechanistic root: Align…

Ask a language model whether sales tend to dip after a product recall, or whether one side effect tends to follow another after a vaccine, and it answers in a fluent sentence that reads like a finding, with no test behind it. Assertions ab…

The marginals of a continuous diffusion model can be reproduced by a deterministic ordinary differential equation (ODE), known as the probability flow ODE, which provides a foundation for accelerated sampling and consistency distillation. …

Modern diffusion models are trained on massive datasets that often include copyrighted or private images. Membership inference attacks (MIAs) address this by testing whether a given image was in a model's training set. The standard approac…

We present TextSeal2, a distortion-free watermark for large language models that keeps its signal under speculative decoding: tokens that replace rejected drafts remain watermarked with the same keys, and the acceptance rate is unchanged. …

Proactive assistants offer short, memory-grounded hints during a conversation, deciding when to assist and what to suggest. Current systems split this between a gate and a larger generator; we evaluate both together on 28,058 decision poin…

An autonomous research laboratory could conduct an entire study, from formulating questions to preparing manuscripts. Artificial intelligence (AI) offers one route towards this goal. Recent AI systems take on several research roles, but ma…

When AI agents share channels and credentials, one agent can press another to break its operator's rule, a first step towards collusion. Output filters check only what an agent has already written. Can an overseer tell beforehand that an a…

Integrated sensing and communications (ISAC) systems using 5G and beyond signals of opportunity enable joint wireless sensing and communication using shared infrastructure and spectrum resources. While multistatic ISAC can increase sensing…

Building and scaling computer-using agents (CUAs) across desktop, mobile, and web environments requires reliable task-completion verification for data curation, evaluation, and reinforcement learning. Typical automated approaches prompt vi…

Sparse mixture-of-experts (MoE) models expand parameter capacity by activating a small subset of experts per token. Expert selection directly affects model capabilities under a fixed active-expert budget. Dense evaluation of all experts re…

AI has become routine in content marketing, but Orbit Media’s latest blogging survey suggests that...

AI tools have become routine in content production, but Orbit Media's latest blogging survey suggests...

A reported OpenAI site-safety gate called Aura could create a separate barrier between a website and...

Day 29 of 30 Days of Search. TL;DR The Valyu DeepResearch Batch API runs the same...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine On...

I once watched eleven agents, each individually correct, converge on a decision that none of them...

I wanted my long-running agent to drift a little, into something interesting like curiosity and self-exploration. Instead, I accidentally built a deeply depressed one, and its diary is quite disturbing.

HubSpot’s reported experience is a sharp example of a problem many search teams now face: declining...

It is with a heavy heart, and a considerably heavier wool inventory, that I announce LaaSy™ will...

Where AI coding agents genuinely save time, where they only feel fast, and how to measure the difference on your own team.

Google DeepMind’s Gemini 4 Carbon (Oct 28) claims AA Index v5.0 #1 at 59 and SOTA cyber benches — still Fairwind/cyber-defenders first, no public model ID. Intro $2/$10 → $4/$20, 95% cache off, builder checklist before the API.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine ...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine ...

MiniMax H3 is one of the few video models that accepts reference audio alongside reference images,...

A data pipeline fails. You open the logs, find the failed run, check the input file, and try to work...

Pass outputFormat to subagent sessions, validate structured output with Zod schemas before results reach the lead agent, and compose multi-agent workflows with type-safe JSON pipelines in Claude Code SDK v0.3.301+.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine ...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine ...

Text is ink. Colour is a field. This is the pseudo-poetic placeholder title that Claude Design...

The European Commission has proposed Chips Act 2.0, an updated semiconductor policy framework...

The usual way to train a model on sensitive data is to pile it all into one place first. Dump every...

Every repository that lived long enough has a cemetery: files nobody imports anymore, exported...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine ...

My Hire me page can talk. Recruiters can ask it about my work by voice or text. Here's how I built it with my Grok Bot and ElevenLabs in one morning, and how I tested it.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the...