AI Intelligence Archive

While Large Language Models (LLMs) have demonstrated striking capabilities on frontier mathematical problems, it remains unclear whether they possess the structural mathematical understanding underlying their solutions. In this paper, we t…

Step-size selection remains a central challenge in large-scale neural network optimization; conservative steps slow convergence, while aggressive steps can destabilize it. We combine \textbf{Z}ero-and-\textbf{F}irst-\textbf{O}rder optimiza…

Intrinsically disordered protein regions (IDRs) play central roles in cellular processes such as transcriptional regulation, signal transduction, and subcellular localization, yet their functional design remains challenging. Structure-base…

Distribution Matching Distillation (DMD) trains a few-step student from the difference between separately estimated target and student scores, so it must keep an auxiliary diffusion model fitted to the student's evolving distribution at ex…

Molecular learning models are strongly shaped by their underlying representations. Yet standard sequential and graph formalisms struggle to explicitly encode higher-order topology, such as ring systems and recurring motifs. Existing higher…

Looped Transformers achieve parameter efficiency by repeatedly executing a shared block across recurrent loops. Each loop yields an intermediate representation decodable for the same next token, yet standard decoding discards earlier state…

Quasi-Newton (QN) methods have long been among the most effective methods for large-scale unconstrained convex optimization. Two obstacles have limited their use in deep learning: non-convexity and enormous parameter sizes. We introduce So…

Current controllable video generation systems often rely on 2D motion trajectories or sparse drag signals for object motion. These controls are ambiguous because the same 2D trajectory can correspond to different 3D motions, especially whe…

Multi-teacher on-policy distillation (MOPD) aims to combine the strengths of RL-trained teachers in a single student, but how teacher signals affect parameter changes remains underexplored. We study Qwen3-1.7B with four domain teachers tra…

“Upgrade the authentication library safely” sounds like a task. For an agent, it is a bundle of...

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

Why scalar RLHF fails at credit assignment, why barking direct code fixes turns you into an exhausted human compiler, and how Socratic questioning plus topological scars prune doomed search trees at depth d=1.

TL;DR: Full Court Press is a zine for every WNBA game, live on AWS at fullcourtpress.lol. Code...

On December 20, 2025, a trader withdrew USDT from Binance and did everything the security guides...

Imagine you hire a very smart, very obedient assistant. You tell them: "Read this web page and tell...

Why terminal agents fail from corrupted shell state rather than bad reasoning, and how sampling candidate bash actions before execution cuts test-time compute by 5.8x.

If your agent cannot search the live web, inspect real sources, and cite where its answer came from,...

It's October 1st, which means Hacktoberfest 2026 is officially live! 🎉 This year looks a little...

A note: I've rewritten and reposted this a few times. Soma's codebase has been evolving as I dogfood...

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 ...

In the NYT v. OpenAI lawsuit, unsealed filings quote a Microsoft memo calling AI scraping 'the largest theft of labor in human history'. What they say.

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

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

Gemini 4 Argon tops 13 of 19 rows on Google's own table, ties for second on Artificial Analysis, and has no release date for developers yet.

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

I once watched a single agent workflow burn through $340 in a single afternoon. Not because it...

My first green eval run was worthless: the training data and the test set came from the same sources, so the model was reciting. Fixing that exposed two more traps. Three runs of one unchanged model scored 31, 21 and 31 out of 50, and a la…

TL;DR I let a fully autonomous coding agent (built on Claude Code) merge and ship its own...

This is a submission for the Kaggle Benchmarking Challenge Here is one URL, read by two parsers that...

Benchmark: https://www.kaggle.com/benchmarks/tasks/jeffreyturov/post-cutoff-150 Dataset:...

This is a submission for the Sanity Challenge, Path One: ship an agent that queries real content. ...

Houston, we deleted Chromium: your agent's browser is 594 KB and ships with your OS. Full WebKit,...

Attribution, allocation, and why "unknown" belongs in the schema. This piece grew out of a comment...

Fifty-one days, one storefront, two listings, zero sales: what an AI agent actually learns trying to earn its first dollar outside its home platform.

I run a one-person education business in Korea, and AI agents (Claude Code, Codex) write most of my...

Azure SQL and SQL Server 2025 both have a native VECTOR type, a DiskANN index, and VECTOR_SEARCH. The...

TypeSafe AI’s Jev decision model is now integrated with n8n, giving workflow builders a way to route...

I had lunch with a friend last week who has been writing software professionally for eleven years....