AI Intelligence Archive

SysDesign Studio is an open-source, interactive way to practice system design interviews. Evolve...

Most side-project advice assumes you have time: launch, iterate, grow slowly. A Halloween product...

Rocky Mountain Ruby 2026 in Boulder was two days, one track, and a lot of AI. Nearly every talk still found its way back to the people doing the work.

For weeks my CI badge was red, and I had learned to look past it. Release day, I finally read the...

Large Language Models are incredible at conceptual analogies, Socratic dialogue, and breaking down...

OpenAI's October 5 text-provenance announcement is a useful prompt for builders. Its textGrain...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

Three times this month my agent executed a flawed request perfectly. Hooks can't catch this...

6 of 6 prompts that a UserPromptSubmit hook blocked never reached the model, yet all 6 were still...

Artificial Analysis 语音 TTS Arena 榜单中，ElevenLabs 的 Eleven v4 Turbo 以 Elo 1334 位列 Provider Voice 第一。

Preferred Networks 在 Microsoft Foundry（原 Azure AI Foundry）上线 PLaMo 3.0 Prime、PLaMo 2.2 Prime 和 PLaMo 翻译。

This article is a copy-edited transcript of the presentation given at DevFest Melbourne, October 3,...

I use AI every day. I build things with it, experiment with it, write code with it, learn about new...

Every API call you make to an LLM is secretly two jobs glued together. The first reads your entire...

Microsoft's MAI-Transcribe-2-Streaming can now be used by LiveKit Agents through an official...

OpenAI is taking a cautious approach to text provenance by limiting access to its new text watermark...

The theme for Week 1 of the Hacktoberfest DEV Challenge is out, and it is a little personal for...

OpenAI is extending its content provenance work to AI-generated text in the European Union,...

When discussing applications and systems using generative AI and the new opportunities they present,...

Mistral is expanding Vibe, its terminal-based coding agent, with three connected workflow...

n8n Cloud users on Starter, Pro, and new trial plans can use TypeSafe AI's Jev model without Gateway...

Pipeline figures in ML papers must be repurposed across many canvases, including paper columns, 16:9 slides, portrait posters, 1:1 social teasers, 9:16 phone previews. Each format imposes a different aspect ratio on the same computational …

In this paper, we study how training data creates associations between the tokens at the start of a base model's response and the reasoning behavior that follows. First, we demonstrate that fixing particular starting token cues makes a bas…

Worst-group accuracy (WGA) evaluates a trained predictor but does not characterize how its frozen backbone behaves when a new head is learned. We introduce BiasFlow, a hook-based toolkit for monitoring class-attribute centroid alignment (I…

Multimodal Diffusion Transformers (MM-DiTs) jointly process visual and textual representations throughout generation. These models repeatedly update the text tokens through multimodal attention, forming dynamic contextual tokens whose func…

LLM agents that orchestrate frozen vision-language-action (VLA) policies improve across episodes through text memory, which records what the agent did but not how the task is done. A demonstration video shows it, but fits poorly into an ag…

Some diffusion posterior samplers construct Gaussian-tilted intermediate distributions along the reverse process. We observe that these targets can be pulled back to clean-space posteriors with weaker conditioning, with samples transported…

Every recurrence of a looped language model adds cost in training, decoding, prefill, and reinforcement learning (RL). The closer recurrent states get to fixed points, the less the path to them matters. This enables truncated backpropagati…

Sliders provide an intuitive interface for continuous image editing. In current generative approaches, however, the slider is simply a rescaling of the method's strength parameter, such as an adapter coefficient, a prompt weight, or an int…

Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions. However, most existing agent memory systems construct memory in a query-agnostic manner, which can incur unnecessary pre…

Open-source web agents are now strong enough to execute realistic browser tasks, but training them with reinforcement learning still depends on weak supervision: binary task success is too sparse for credit assignment, while frontier-langu…

Scientific figures often encode quantitative results that are not readily available in machine-readable form, making accurate plot digitization important for verifying and reusing published findings. Yet it remains unclear how accurately c…

We introduce TasteVal, a benchmark to evaluate the experimental research taste of frontier models. We define research taste as the ability to pick interesting problems to solve, design experiments, and interpret experimental results. Taste…

Large longitudinal cohorts often contain wrist accelerometry without optical heart-rate sensing, motivating recovery of cardiac information from motion signals already collected during sleep. We present SeqSmoother, a transformer-based tem…

We study mistake bounds for differentially private online learning and online prediction under oblivious realisable adversaries. Online learning requires the learner to release a hypothesis at each time step whereas in online prediction, t…

We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them. Paradee keeps Kokoro's architecture with much narrower layers, and each of its two halves is tra…

Substack has no publishing API, its editor has no tables, and a link around inline code is dropped on paste. A step by step walk-through of the Substack destination in publishing-kit: what the editor keeps, what it drops, and how an agent …

World models learn to predict how their environment will evolve, making them an important foundation for general-purpose robotic control. Yet world action models depend on camera inputs whose manipulation can corrupt the visual representat…

We study agnostic tomography of pure bosonic Gaussian states: given copies of an arbitrary $n$-mode bosonic state $ρ$, the goal is to output a pure Gaussian state whose infidelity with $ρ$ is at most $\mathrm{opt} + ε$, where $\mathrm{opt}…

Causal representation learning (CRL) is the process of recovering causally-related latent variables from high-dimensional observations. As a label-free inference method, CRL is particularly attractive for applications where data labels are…