AI Intelligence Archive

OpenAI and Cerebras have confirmed a multi-year partnership to deploy 750MW of Cerebras wafer-scale...

Notes from about 25 coding-agent tools and published setups and six recent papers. Agents follow what...

A model handed a bug will hand you back a plausible fix and a green test suite in about a minute. That tells you almost nothing.

Kaggle Benchmarking Challenge. Previously: Day 0, the benchmark · Day 1, most of my bugs looked like...

Samajh — a reader for the letters my mother couldn't read The letter Every few...

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...

The software factory assumes agents reviewing agents catches what tests miss. I gave 77 cheating diffs to three reviewer models. They caught every exotic cheat and waved through the assertion that was quietly made unfalsifiable.

Welcome to the Vector Database Showroom — a guided tour through today's most popular vector...

Picture this, you open a PR and the AI report is already waiting. Three findings, all minor. You skim...

Cloudflare's Clef scores decisions. Build a tiny TypeScript gate that turns scores into act, ask, or skip, with a human boundary for refunds.

Markdown is easy to write and hard to publish. Every destination renders it differently, two have no API, and the failures show up only after you hit Publish. A step by step walk-through of publishing-kit, an agent skill that builds, check…

Google has strengthened its guidance for publishers using generative AI, stating that it is critical...

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I...

Meta Muse security: any local process can redirect the account token, and Muse zipped its own 6.8 GB sandbox on request. Meta's bounty: Not Applicable.

How a support case composer went from "suggest a React snippet" to a declarative catalog with A2UI...

UpGuard Research looked at about 300,000 domains that use Supabase and found 16,326 databases...

Most MCP servers get tested the same way: connect one client, call a few tools by hand, ship...

This is a submission for the Kaggle Benchmarking Challenge. What I Benchmarked Twelve...

Routing LLM requests by cost and latency means sending each request to the cheapest or fastest model...

Microsoft AI voice models are now available in LiveKit Agents through an official Microsoft AI...

A few years ago, building with AI usually meant one thing: send some data to a model, get a...

A regional sales manager and a sales rep both ask the same Foundry agent the exact same question:...

This paper examines the role of Novel View Synthesis (NVS) in geometric representation learning. In principle, NVS should reason about 3D scene structure, thereby enabling transferable multi-view geometric representations. Yet, existing en…

We introduce 4DCodeBench, a benchmark for 4D inverse graphics through code generation, in which agents reconstruct dynamic scenes from video as executable graphics programs. To accomplish this, agents must translate visual observations int…

Continual learning treats degradation on previously seen data as evidence of failure, a convention inherited from settings with a stationary prediction target, where a correct label remains correct indefinitely. World models do not satisfy…

Ribonucleic acid (RNA) functions through conformational changes that are not fully captured by static structures. However, large-scale standardized RNA dynamics data remain limited, and existing approaches typically treat trajectory genera…

Inspired by human vision, we introduce a framework using active gaze to enable fine-grained bimanual manipulation with only a single stereo camera. EyeRobot 2.0 physically attends to a 3D fixation point in the scene by swiveling two eye vi…

We study the minimization of sums of smooth strongly convex functions over undirected graphs, with each function held by one agent and communication restricted to neighbors in the graph. Existing decentralized methods, whether based on gos…

The choice of post-training data for large language models substantially affects downstream performance. Gradient-based data selection is a popular approach that ranks training data by how well their gradients align with those of a small v…

Modern chess engines are silent experts: they play at a superhuman level, but do not offer explanations for their play. On the other hand, language models (LMs) can generate plausible-sounding explanations, but their weak playing strength …

Scarcity of labeled data limits development of deep learning biomarkers in oncology. We develop a two-stage AI model predicting pathological complete response (pCR) to neoadjuvant therapy in breast cancer. The first stage learns the transc…

Why I did this I created SnoozeStack — a backend platform with a specific bet: most...

The dynamics of cells, organisms, and fluids are often modeled as probability distributions evolving over time. Reconstructing and extrapolating this evolution from unpaired snapshots requires assumptions about the underlying process. Wass…

Microsoft has expanded distribution of its MAI voice models to OpenRouter, adding a cross-platform...

LLM-guided evolutionary methods, such as AlphaEvolve, have emerged as powerful approaches for challenging computational optimization problems, such as circle packing. However, prior work typically optimizes performance gain over a fixed nu…

In July I wrote that agents need governed memory: memory with its own lifecycle that decays, gets...

You tell Claude Code that you deploy only from the release branch. An hour later you open Cursor, ask...

Policy-gradient methods are central to modern reinforcement learning, including LLM post-training. When they struggle, the usual suspects are exploration, credit assignment and action-sampling noise. Classification has none of them. A clas…

Masked diffusion language models (dLMs) offer a promising parallel alternative to autoregressive models for complex reasoning. However, they face a distinct credit-assignment challenge, since a few commitments during denoising sharply redu…

Deploying a new decision policy creates a cold-start problem for prediction models whose targets depend on the policy's actions: historical observations reflect earlier policies, while real observations under the new policy are not yet ava…