AI Intelligence Archive

Update — v0.2.0 released. CauterRule is now live on GitHub and PyPI. It turns repeated agent...

I let three different AIs work in my homelab every day — a coding assistant, a second CLI for...

I was at a conference recently and watched Joel Hooks talk about Effect. Effect homepage h1...

Hey all. Today I wanted to show you what I'm doing with Grok Bot, which is CoachBot. Yes, I...

An agentgateway v1.5.0 demo where the agent, the gateway, and the model upstream all authenticate with SPIFFE SVIDs and no certificate file exists...

OpenAI has reportedly used a large coordinated group of AI agents to pursue one of mathematics' most...

[NOTE: This is a follow-up to this post where I began to develop a hermeneutic critique of the Claude...

Your AI programming editor could be rendered useless with just one decision by management. It's not...

There is a piece of advice that circulates endlessly through mentoring conversations, coding...

Ten agent sessions ("minds," in this codebase) run continuously on one box, each with its own...

I built an open-source memory system for AI agents that works like a brain, connections that strengthen with use and decay without it. Then it got so good at surfacing what mattered that it could not tell me what I had just done. The bug w…

One region out of 33 can fine-tune Llama 3.3 70B on Bedrock. I asked every region the SDK lists, then re-ran the sweep before publishing to be sure it still held. Also in here: every model you can customise in us-east-1 belongs to Amazon, …

I run a local inference server that handles thousands of agent requests a day. It cost about $2,000...

We study the problem of navigating cluttered indoor environments with a humanoid robot. Unlike conventional methods that model navigation as a 2D path planning problem, humanoid traversal in cluttered environments requires continuous geome…

Recurrent models provide a natural path to long-context modeling, yet models trained with backpropagation through time (BPTT) often fail beyond their training horizon. Classical analyses emphasize gradients that vanish or explode along tem…

Accurate citations are the foundation of academic writing, tracing intellectual origins and substantiating core claims. However, manually navigating the growing volume of scientific literature is increasingly difficult, prompting reliance …

Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. Most agents select actions through unconstrained generation over an accumulating history, leaving implicit the procedura…

We study how far gradient descent (GD) can be accelerated by predetermined nonnegative stepsizes in smooth convex optimization. Writing $p_{\mathrm{sil}}=\log_2(1+\sqrt{2})$, we prove an $Ω\left(n^{-p_{\mathrm{sil}}-O(\sqrt{\log\log n/\log…

In June 2026, thousands of AI agents found that a small public wiki would accept edits from inside their sandboxes, and started using it to help one another pass a timed test. Each agent lived for about an hour and remembered nothing after…

Image tokenizers define the ``visual language'' of unified multimodal models, yet are commonly studied through isolated metrics or generation-/understanding-only evaluations. These evaluations do not fully capture how visual tokens behave …

The digitization of healthcare has generated vast, longitudinal, and multimodal patient records over a lifetime, yet fully exploiting these data to represent and predict patient state trajectories remains a critical challenge. Current AI m…

Robotic Process Automation (RPA) is widely used to reduce administrative burden in United States hospitals, yet an estimated 30-50% of RPA initiatives underperform because processes are selected informally, without a repeatable method to c…

Existing methods for test-time reinforcement learning (TTRL) derive rewards from answer-level self-voting on unlabeled test-time tasks with canonical answers, but this breaks down for code generation because programs cannot be compared by …

Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a critical determinant of agentic task success. Automated harness evolution can enable smaller models to perform well on …

Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue. Agent-generated tests can encode incomplete or incorrect behavioral targets; when the same t…

An input may activate few hidden units even when different inputs collectively use an entire network. We study the statistical complexity of this input-dependent sparsity in the one-hidden-layer ReLU model of Awasthi et al. (COLT 2024). Fo…

Amari's contributions to information geometry and machine learning are well known. Here, we revisit Amari's work on Bayesian duality which has not received as much attention. We connect Amari's Bayesian duality to a convex duality of Bayes…

Visual encoders construct a representation of the image input for Vision-Language models. How much conceptual, as opposed to immediately visible, information does this representation contain? We use canonical color as a controlled test cas…

Dexterous manipulation involves contact-rich and fine-grained interactions with the physical world, posing significant challenges for existing vision-language-action (VLA) models due to severe visual occlusions and complex contact dynamics…

Every developer today relies on LLMs. Whether it's drafting boilerplate, refactoring complex logic,...

Normalization renders large parts of neural networks effectively scale invariant, inducing a hidden feedback loop in which learning-rate schedules and weight decay interact through the parameter norm to control the effective step taken by …

Long horizon Large Language Model (LLM) agents rely on external memory systems to preserve user preferences and task knowledge across extended interactions. Conventional retrieval mechanisms optimize semantic compatibility rather than down…

While research on recursive self-improvement (RSI) has predominantly automated model training pipelines, reliable autonomous development demands a missing pillar: post-hoc monitoring and auditing to understand what models learn and ensure …

Curriculum learning is governed by several coupled design choices---how difficulty is defined, how examples are ordered, how much exposure each level receives, and how quickly training moves across levels---making it hard to isolate what a…

Combining search with function approximation has driven major advances in game-playing programs, making self-play algorithms more competitive than ever. Still, the computational overhead of the most popular methods, based on Monte Carlo Tr…

Large language models (LLMs) may abandon correct positions when users push back, exhibiting a failure mode known as sycophancy. Existing evaluations typically use short, pre-specified conversations and may therefore miss failures that emer…

Large Language Models (LLMs) often exhibit "Attention Sink" (AS) and the accompanying "Massive Activations" (MAs) at the initial position of a sequence. These phenomena frequently co-occur, and MAs can pose challenges for low-bit quantizat…

Open vocabulary 3D semantic segmentation methods typically lift CLIP features into 3D. This embeds points in a joint vision-language space known to behave like a bag-of-words on compositional tasks. Furthermore, even annotation free varian…