AI Intelligence Archive

Your security team can't review every pull request by hand. Static analysis tools like Semgrep and...

LLM Price Watch Weekly Digest No price changes this week across the five providers we...

A friend sent me two screenshots. His terminal was full of this: Hook error: POST...

How Caveman Ultra Mode compresses coding-agent replies, where it helps most, and how to preserve evidence and judgment when working tersely.

Stratagems #26: Lena Cut a Branch. The AI Got the Message. Punish the branch. Deliver the...

A model wrote a patch that could not possibly fix the defect. My test passed it. Neither was careless — both had compressed the same English requirement the same shallow way, so the green checkmark was manufactured by two independent error…

An AI agent does not automatically need a custom RAG pipeline to use organizational knowledge. If the corpus is maintained, searchable, structurally readable,…

Give Claude Code an editable knowledge base by connecting a narrowly scoped MCP server that exposes structured search, versioned reads, and block level writes.…

Tropical cyclones are among the deadliest and costliest natural disasters on Earth, responsible for...

Last week I wrote about building a French AI voiceover API that only accepts payment from robots — an...

To mitigate the time complexity of generative models, one-step generative models have recently emerged through direct mapping from noise to data in a single forward pass. However, the reward-guided fine-tuning method of one-step generative…

Large language model (LLM)-based agents have shown strong potential in solving complex tasks through multi-step reasoning, yet they remain vulnerable to execution failures. Accurate failure attribution is therefore critical for improving a…

Attributing an artwork to an artist has traditionally relied on detailed visual observations and descriptions, known as stylistic analysis in art history. By contrast, current artificial intelligence (AI) models used in the field offer onl…

I wrote this post for the purposes of entering Google's **All Things Agentic Hackathon* (Track:...

Generative AI applications are rapidly moving beyond single-turn conversational chatbots toward...

Large language models (LLMs) have shown promise for spatio-temporal forecasting, but existing approaches often rely on regularly sampled token sequences and struggle with irregular observations because of temporal asynchrony, representatio…

There's a specific kind of night: you lie down having finished half your list, and the only thing...

We study unsupervised hypergraph alignment, where the goal is to infer node correspondences between two hypergraphs using only structural information, without node features, labels, seed matches, or side information. Direct higher-order fo…

Most developers install our tools through an AI agent now. Watching agents guess at our human docs, we started shipping a machine-first documentation.ai.md — and open-sourced it.

Another one from the same one-person-AI-company setup I've written about before: Claude Code builds...

Built a .NET invoicing library with Claude Code over about a week. Zero dependencies, VAT and GST...

Building a full-stack mobile app by yourself is hard. Building it for a major hackathon like Shipaton...

There is a very specific rush of dopamine you get when you finally configure your keystores, set up...

Natural Language Processing methods have enabled novel solutions and advances in the field of privacy, particularly in the sub-domain of text-to-text privatization, where the goal is to transform a sensitive input text into a privatized ou…

Recent advances in large reasoning models (LRMs) have shown strong performance on complex problems through long chain-of-thought (Long CoT) reasoning. However, distilling such trajectories into smaller student models remains challenging: d…

Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs), yet existing RAG systems often struggle with complex, multi-step reasoning that requires adaptive retrieval and continuous revision of intermedia…

Long-horizon story-driven video generation requires a production agent to coordinate narrative decomposition, state tracking, shot design, prompt construction, rendering, and revision across interdependent scenes. Existing adaptive video s…

This paper introduces a hybrid fact-checking framework that integrates Knowledge Graph-based semantic memory with adversarial multi-agent reasoning for explainable misinformation detection. The proposed system follows a memory-first, web-f…

Criminal judgment prediction requires models to infer statutory articles, charges, and sentencing outcomes from case facts. Unlike standard classification tasks, it involves a structured reasoning process in which statutes should be matche…

Across industries, machine-learning systems support applications ranging from prediction and anomaly detection to forecasting, optimization, and scheduling, yet operationalizing these systems requires coordinating application development, …

Function vectors (FVs) have recently emerged as a promising mechanism for steering the behavior of large language models (LLMs) by injecting task-specific latent direction representations derived from in-context demonstrations. While prior…

Sustained scientific work requires a knowledge substrate that carries interpretation across tasks and preserves paths to source evidence. We call this process \emph{scientific knowledge compilation} and implement it in ASKS, the \emph{Agen…

本周最佳两篇 Week 35 Accelerating Scientific Research with Gemini in the Real-World https://arxiv.org/pdf/2608.26701 Automated Researchers Can Reliably Mitigate Alignment Failures https://www-cdn.anthropic.com/7b1c44894e980876479947dcdd40716278a…

The current alignment tuning paradigm for Large Language Models (LLMs) prioritizes surface-level behaviors -- fluency, safety, and tonal consistency. While effective for casual chat, this thesis argues that such surface alignment masks a l…

Machine learning is usually evaluated after an evidence interface has been fixed. A dataset, sensor suite, query language, action set, or experimental protocol determines which observations can be obtained, and learning is judged by what i…

Large language model (LLM) agents need durable, faithful memory of everything a user or organization has said and stored, yet most memory systems commit to a single organizing structure (a fact store, a vector index, or a knowledge graph) …

Memory operations of long-horizon LLM agents are hard to supervise: an operation's value is unobservable when it is taken. But they are special -- they leave machine-readable evidence in the trajectory: retrieval hits and answer-time citat…

On July 30, OpenAI cut GPT-5.6 Luna to $0.20 per million input tokens and $1.20 per million output —...

A Japanese version of this is on Note. An increasing number of engineers and creators are running...

We present $\mathcal{N}_0$-Foundation, a paradigm for tactile-enabled embodied manipulation, which integrates tactile sensing hardware, large-scale multimodal data, tactile representation learning, and standardized evaluation. First, we en…