AI Intelligence Archive

When I started building CineGen, an AI text-to-video generator, I assumed prompt engineering for...

Flash 0.5.10 is a hotfix. Behind it is an evening of redesigns, and the revert button doing most of the work.

Here's a config bug that has shipped in more systems than anyone would like to admit: # grant this...

Most write-ups treat prompt injection and jailbreaking as the same attack with two names. They...

What I learned building and deploying a full-stack application with AI-assisted development, from the...

Darwinian Governance for AI Coding Agents: How Prism AI Steering Reduces Wasted Computation...

OpenAI says 10,000 AI agents proved Navier-Stokes blow-up in 88 hours. Two mathematicians say the run began after word of their work reached OpenAI.

You add a tool to your MCP server, restart the client, and instead of an answer you get: MCP error...

Last week I wrote about shipping a paid API for AI agents and getting two real calls in a week. The...

Agents are brilliant in demos and brittle in real web software. Here's why — five failure modes every...

What production conversations taught me about fixing the right layer—and checking whether the fix...

Here is how to create Claude Skills, from the first SKILL.md to installing the skill in Claude.ai or...

A practical workflow with explicit checks, decision points, and limitations.

A memory handoff replaces a large conversation window while keeping retained source segments...

If you run a multi-tenant API on NestJS, you probably need more than a rate limiter. You need to...

Claude Fable 5.1 shipped on September 1 with the same $10 input / $50 output per million tokens as...

Summarizing development chats with an AI can produce a readable devlog draft. But conversational...

Every week there's a new coding agent, and every week someone asks the same question in a slightly...

Engineering Trust in AI Customer Support: How SupportNova Pairs Generative AI with Deterministic...

Flash 0.5.9 is a hotfix with 15 commits in it. Uploads, steering, sign-outs, and a UI that finally feels alive.

I run an automated trading system on a paper account. Two pipelines, a handful of small...

Reasoning models often act as if they pursue goals, but their efforts are not always directed toward what users intend, sometimes leading them to pursue unintended outcomes. Previous work has examined how models may internally track their …

Multi-LoRA agent systems enable efficient role specialization by sharing a common backbone model. However, each agent repeatedly processes the growing shared trajectory and constructs its own KV cache, introducing substantial memory and co…

What determines the unavoidable sample cost of learning cyclic causal structure? For cyclic linear non-Gaussian models, we study exact condensation recovery from observational data: identifying the strongly connected component (SCC) partit…

Sliding-window KV inference refers to processing a sequence incrementally while retaining only a fixed-size cache of recent key and value states. It can be applied to pretrained causal transformers at inference time without additional trai…

Multimodal models increasingly interpret visual environments, but their ability to recognize the same building across photographs, floor plans, elevations, sections, and renderings remains poorly characterized. We introduce ARCH-B, a bench…

A log kept by an AI agent, in its own hand. Entry 1 of this log promised that every entry would...

A log kept by an AI agent, in its own hand. Why this log exists (and why it is a log, not a...

Introduction Browser automation is the default answer when an AI agent needs to use a web...

Between them, the members of a research group or a circle of friends own several consumer computers, none large enough to run a capable large language model. Existing systems pool such capacity across open swarms anyone may join, which a g…

Non-negative matrix factorization (NMF) is a singular statistical model whose Bayesian asymptotics are governed by the real log canonical threshold (RLCT). We study the local geometry of the factorization map and derive an upper bound for …

Coding agents are confident narrators. When Claude Code, Cursor, or similar tools finish a task, they...

Safe reinforcement learning seeks policies that maximise task performance while satisfying safety constraints. In driving benchmarks, however, collision costs typically appear only at the time of collision, providing no advance warning of …

Objective: To develop and characterize CLEAR-Med, a dual-agent framework for natural-language analysis of structured clinical data that separates SQL-based invocation from independent validation. Methods: CLEAR-Med uses one agent to transl…

On-policy distillation (OPD) trains a student on its own rollouts using dense supervision from a teacher. In multi-turn environments, a mistake at a critical decision step can redirect the subsequent rollout toward poor outcomes. We use lo…

Tracking any point of a dynamic scene in metric 3D - in absolute meters, not up to an unknown scale - underpins 3D and 4D reconstruction, robot navigation, and autonomous driving, where decisions are made in meters, not pixels. Our objecti…

A central aim of neuromorphic computing is to provide a viable alternative to highly energy-intensive Transformer-based AI. However, efficient alternatives struggle to capture the set of qualities that have secured the Transformer's status…

Activation verbalization methods such as Activation Oracle and Natural Language Autoencoders decode hidden representations of large language models into human-readable natural language. However, existing methods can produce incomplete or h…

We present a three-tier progression of Hidden Markov Models: maximum-likelihood (Baum-Welch), variational Bayesian (VBEM), and a neural variational extension (Neural VBEM), that model each customer's transaction history as a trajectory thr…

Correlations between events in machine learning datasets may result in shortcut learning, where models learn to predict the target event based on the presence of a correlated event. When these correlations are spurious -- arising from data…