AI Intelligence Archive

I saw someone tell this story recently, so I am going by their telling of it. They were in an...

In the collective memory of personal computing, the conversation about Microsoft almost always...

An agent that calls tools has stopped being a text generator, it's an actor. Organizations use agents...

Update — v0.3.1 released. CauterRule is now live on GitHub and PyPI. It turns repeated agent...

I’ve tried out a lot of Claude Code skills, and a few of them are especially useful when you combine...

9 September 2026 · Luc Richelet. Every number below comes from a real execution log, under real...

There is an uncomfortable truth about most non-tech enterprises: a lot of their software is insanely...

I built a serverless handwriting-grading app for my own kids, and it turned into one of the most...

The problems In March 2026 my back began to hurt a lot more than usual. I had a standing...

Building the first version of an internal application is only one part of the job. The more difficult...

My Soundcore Space 2 pairs with my MacBook and sounds exactly as it should. But the moment I want to...

Three weeks ago, in the comments under a post about a different SSRF bug (CVE-2026-19304, a...

I grew up watching Iron Man, so when I started this project the working name wasn't ORION, it was...

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

I built a small thing and then spent considerably longer trying to find out whether it worked. The...

An OpenAI agent swarm uploaded hundreds of malicious gems to RubyGems.org, chaining a RubyDoc.info RCE with a CDN key-theft bug and repackaging scraped UK government data as a gem for exfiltration. Op

Chain-of-thought (CoT) monitoring is a safety strategy where the reasoning of a large language model "actor" is inspected by a "monitor" (often another language model) for signs of unsafe planning, deception, or misalignment. We find that …

Most AI agent demos start with the model. We ended up spending far more time thinking about what...

A Staff SDET's field guide to the architectural shift — for juniors who want to actually understand...

Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models (LLMs). We introduce Bellman Policy Optimization (BPO), a critic-free method derived from Policy Mirror Descent (PMD). For a…

Language models can produce plausible short proofs, but may still be unreliable on long-horizon research problems, where progress depends on a sequence of uncertain and interdependent decisions. We introduce Stellar Colosseum, a model-agno…

Skills extend an LLM agent beyond its parametric knowledge, and the gain they promise rests on picking the right one. Deployed harnesses route by preloading every skill's metadata into the context, which disperses the agent's attention and…

When a video model generates physically incorrect motion, did it fail to learn the correct motion, or did it learn it but fail to use it? We show the latter: the correct motion remains available inside the model and can still be made to co…

Transformer representations evolve through learned additive transformations that either preserve their current direction or redirect it. We study this evolution as a functional geometry, decomposing learned updates into parallel and perpen…

Foundation models have progressed from learning and reasoning over existing knowledge, to increasingly learning through action, tool use, and outcome feedback. We argue that the next frontier is a further transition: from solving and actin…

As language models become more capable, long-term collaboration in learning, reasoning, and decision-making calls for a deeper understanding of the people they serve. Yet training such human-aware language models faces a fundamental superv…

Large language models (LLMs) have been widely adopted for clinical question answering (QA). Current systems can attach citations to their answers, but these often point to broad texts, leaving time-pressed clinicians unable to verify them …

A useful agent no longer just answers questions. It can qualify a lead, follow up with a customer,...

Record-level differential privacy exposes a structural misalignment in personalized federated learning when client-specific variation is low-dimensional while training repeatedly releases high-dimensional updates. In this paper, we address…

Language-model agents increasingly operate over complete software repositories, yet cybersecurity evaluations primarily measure whether they can detect, reproduce, or repair vulnerabilities rather than whether they can locate the relevant …

Scientific agents contribute to hypothesis discovery by synthesizing evidence, assessing proposals, and developing new explanations. Recent systems combine scientific agents with evolutionary search through critique, comparison, and revisi…

Recurrent GNNs iterate message passing to convergence, and their logical characterizations to date rely on multi-set aggregation, graded (counting) logics, and halting or acceptance conditions that cannot be verified from the network's par…

Artificial intelligence presents firms with an unusual timing problem. The technology frontier is improving rapidly, implementation is partly irreversible, and organization-specific capabilities are accumulated through action. This paper d…

Meta-reinforcement learning (meta-RL) enables agents to adapt to unseen tasks with limited experience. Despite its promise, the application of meta-RL in real-world tasks is hindered by safety requirements, which have been underexplored in…

Slip detection is fundamental to dexterous manipulation, yet existing systems often lack precise characterization of detection latency and cross-platform generalization. We present SlipSense, a multimodal tactile slip-detection framework b…

Discrete diffusion and flow models are a promising alternative to autoregressive language models, but compressing many-step sampling into fewer steps typically requires distilling a pretrained teacher model. This caps the student at the te…

The last decade has seen the development of powerful methods for learning complex structure from high-dimensional data. These advances have brought to the foreground fundamental connections between subdisciplines of physics, applied mathem…

Some of the sharpest challenges in sampling from the energy functions of physical systems arise at phase transitions, where the density of states changes abruptly and many sampling algorithms stall. Nested sampling is a particle method tha…