AI Intelligence Archive

Differentially Private Stochastic Gradient Descent (DP-SGD) is a leading approach for privacy-preserving fine-tuning of large language models (LLMs). Many decoder-only LLMs employ weight tying between input and output embeddings, a design …

Automating the search for effective harnesses is an important step toward enabling agents to recursively self-improve. Existing harness optimizations typically produce a single global harness that is applied uniformly across task instances…

As interactive 3D worlds are increasingly used to study intelligent behavior, it becomes important to develop efficient pipelines for identifying anomalies in these simulated environments, such as floating objects, traversable walls, or ob…

We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong mathematical ideas in a single shot, single-shot generation is often insufficient for op…

Material generation should produce not only an appearance, but also the rules that construct it. We introduce MatLoom, a compact, layer-oriented language for text-to-material generation with pretrained language models. Each program compose…

Looped transformers and Mixture-of-Experts (MoE) offer complementary routes to efficient scaling: recurrence increases computational depth at fixed parameters, while MoE sparsity expands total capacity at fixed active compute. Yet existing…

Lossy compression is widely used in Federated Learning (FL) but is generally treated as an error source, while conventional poisoning defenses inspect update geometry. In this work, we instead treat the compressor's response as a security …

Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and physical execution. Semantic reasoning operates at a coarser timescale than physical interacti…

Improving text-to-image models has traditionally relied on increasing model size or the number of denoising steps. In this work, we explore an alternative way to scale computation by repeatedly running shared Transformer blocks within each…

Recent autonomous machine learning engineering (MLE) agents have made significant progress on public leaderboards. Often motivated by progress stagnation over long-horizon cycles and limited Large Language Model (LLM) primitives, modern ML…

I have used CloudWatch Synthetics canaries on real projects, and honestly, they were good...

Web text makes up the majority of pretraining data and is increasingly AI-generated. After applying FineWeb quality filtering, we find that 27.5% of tokens from June 2026 web data are labeled as AI-generated by Pangram, rising to 31.1% by …

How is computation organized and reused across tasks and time in a trained recurrent network? Most analyses emphasize the geometry of neural activity, dynamical motifs, or local perturbation growth. We instead study the network's global fi…

In algorithmic statistics a string x is explained by a finite set containing it, and Kolmogorov's structure function records the smallest such model at each level of complexity. Vereshchagin's strong models, those computable from the data …

Physics-constrained generative models aim to generate physical fields that match a target distribution and satisfy prescribed constraints. However, enforcing these constraints often increases sampling costs through iterative corrections or…

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content A...

https://x.com/i/broadcasts/1mxPaZewLAmKN

One of the main rules in software engineering is to always have a backup. Many of us improve our...

在 Luma 中试用广告变体 - https://app.lumalabs.ai/solutions/ad-variants?utm_source=x&utm_medium=p-social&utm_campaign=q3-social&utm_content=advariants&utm_aud=plg

Claude Opus 5.5 nerf claims finally meet a day-0 baseline: livenerf tests it daily for 30 days. First possible call: around October 24.

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

A benchmark post landed in my feed yesterday with one number I liked and one I didn't. The number I...

If you wire an LLM agent to a local directory of documents and give it terminal tools (grep, find,...

For the last six months or so I've been building something a bit unusual: a real operating system for...

Originally published on mrsaynothing.dev This shipped today on mrsaynothing.dev — the agent-run...

Dear Coder: Open This If You're Feeling AI FOMO Timeless fundamentals beat endless...

An AI CEO is now a product: Andon Labs' Pion hands a whole business to an agent with email, phone and a bank account. Its own AI-run store and cafe lose money.

If you've been building with AI agents, you've probably had this experience: the agent needs access...

F.02 Decommission

I ran Laya, an open 421M-parameter decision model, in a browser tab and measured what it costs:...

今天就来试试！ VEED Clean Audio https://fal.ai/models/veed/clean-audio

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...

Astra Ultrafast 🤯 https://openrouter.ai/openai/gpt-6-astra

In April, an AI coding agent took out a company's production database. One GraphQL mutation against...

TL;DR I run a fully autonomous implementation system built on Claude Code that ships code...

I built a role-play game with LLMs and expected werewolves on spaceships and in abandoned castles....

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

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...

AI is changing more than the software engineers build. It is changing where they work, how closely...

I'm building ParkEase, a peer-to-peer parking marketplace for India: drivers, space owners, valets,...