AI Intelligence Archive

Previously: 9 Bugs That All Looked Like a Working System · I Built an AI That Rewrites Its Own...

Three seasons, thirty-six parts, one clinic app — and a meter that ran the whole time. Every part of...

Local inference that actually runs. Your smart camera is not smart. It's a snitch with a monthly...

GPT-6 Astra is the first model OpenAI rates 'Critical' for cyber capability. What that label means, and the tool-permission gate your agent needs anyway.

tldr Subagents architecture made of parallel read-only child agents with simple text...

I use AI coding agents a lot. And for a while, one of the most annoying parts had nothing to do with...

A tutorial for gh stack, and for the fact that it does not care whether the diff gets read by my lead or by an AI. Small diffs get reviewed better either way.

The current generation of AI coding agents makes it surprisingly easy to create a "skill." Write a...

Your AI stack works fine with one model. The moment you add a second provider, a fallback, a rate...

Table of Contents Why Run an AI Model at Home? What Is a Local LLM? What Kind of Computer...

Many recurring text functions are easy to describe but difficult to implement with rules, while calling a large remote model for every input introduces repeated cost, latency, and dependency on a provider. We present compile by training, w…

Language-model judges now gate training data, score generations, and drive leaderboards. The judge is then a measurement instrument, resting on one rarely stated assumption: the same request, sent to the same model name, reads the same tom…

Evolutionary prompt optimizers such as GEPA suffer from prompt bloat: each iteration appends rules and caveats, producing prompts up to 3$\times$ longer yet no more accurate. We trace this to three deficiencies - incomplete error observati…

Reasoning traces from chain-of-thought models appear to offer a legible window into how a model arrives at its answer. A growing body of work treats them as such, using LLM judges to diagnose errors, evaluate faithfulness, and provide step…

Video editing spans diverse editing paradigms, yet achieving high-quality instruction-guided and subject-guided editing within a single unified framework remains challenging. We introduce EditVid, a training-free framework combining sparse…

We introduce the first Probably Approximately Correct (PAC) learning framework for general-sum concurrent stochastic games (CSGs) with transition uncertainty, while addressing the challenge of Nash equilibrium (NE) existence. Our algorithm…

Weakly-Supervised Dense Video Captioning aims to localize and describe multiple events in untrimmed videos given only an ordered set of event-level captions per video. Recent work synthesizes auxiliary transition captions via LLM to provid…

Gaps remain in our understanding of how large language models (LLMs) acquire knowledge during pre-training. We posit that auxiliary views, reformulations of knowledge, are causally helpful for learning. We design controlled experiments to …

Explaining why a specific outcome occurred, and which inputs deserve the blame or credit, is central to philosophical, scientific, and policy analysis. Existing tools split into two camps. The theory of actual causality (AC) gives principl…

For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that inform us about failure cases. As models get stronger, standard benchmarks for machine translation are approaching sat…

On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision from a teacher. Existing work has mainly studied its algorithmic behavior, leaving the role of training data unclear. We examine this role …

Multi-agent AI science ecosystems rely on agents possessing tools that allow them to communicate, coordinate, and build on each other's work. Yet this shared infrastructure can also introduce vulnerabilities by creating a substrate for the…

As edge-based deep learning applications become more complex, optimizing performance on heterogeneous System-on-Chips (SoCs) presents unique challenges. Traditional pipelining techniques distributing the computation across different on-chi…

Repository-level software engineering benchmarks have significantly advanced the evaluation of coding agents, but existing benchmarks primarily measure whether generated patches pass functional tests and overlook review-derived acceptance …

Refereeing the memory-safety retrofit argument from someone who ships framework code in both Rust and Go, and likes them for different reasons.

Research and news coverage of language-model deception increasingly attributes human-like mental-state concepts to language models. Such claims can blur the distinction between behavior that looks deceptive and a mechanism that is actually…

Parameterised graph theory studies how the complexity of graph-theoretic problems depends on structural parameters of the input graph. This perspective has proved useful in analysing tensor-network simulation (Markov and Shi, 2008). Its im…

Large language model (LLM) agents are increasingly proposed as autonomous SOC analysts, but two limitations make them unreliable at enterprise scale: a finite context window cannot hold a multi-thousand-host authentication graph, and free-…

As terminal-based code agents become prevalent, agent trajectories have accumulated at scale, while realistic, executable environments remain scarce. However, environments are what agent post-training actually requires: each can be re-quer…

This paper presents a low-cost, open experimental platform for research in end-to-end autonomous driving with miniature Ackermann vehicles. The platform combines a physical vehicle, a printed urban track, data collection tools, trajectory …

AI agents are trained on population-scale data to encode broad capabilities spanning those of many practitioners. Yet the artifacts they produce rarely meet the personal bar professionals need to stake their reputation on. On realistic, op…

GPT4All is an open-source graphical desktop application for running large language models (LLMs)...

Every review checklist ever written was built for a diff whose author could explain it. Here are the twelve questions that replace that assumption, why the generated tests don't count as a second opinion, and four merge gates that are actu…

A friend of mine doesn't speak English. I do most of my podcast listening in English. Every so often...

In 2001, in the final year of my Computer Science degree, I chose A_I and Neural Networks_ as an...

People have started telling me that my writing sounds like AI. I published that sentence in a...

About a year ago, I wrote a piece called Software Becomes Disposable, arguing that AI was...

Sealing the host made the naive mutation impossible and the agent useless. The fix is a Bench: a disposable environment that starts with no files and no network, where every capability is granted narrowly, per task, and revocably.