AI Intelligence Archive

Large language models reuse the same attention heads across tasks, but identifying these shared heads does not explain what they do differently in each task. A natural source of inspiration is task-dependent interactions among shared brain…

A concrete example connecting slot_mapping, block_table, cache layouts, and tiled attention.

As AI agents increasingly rely on external tools, accurate retrieval is essential for reliable behavior. Existing methods optimize semantic relevance but largely ignore tool availability during execution. To address this gap, we propose RA…

Personal agents increasingly connect to services across the web and applications by using tools. As the effects of their actions accumulate and interact across services, unintended or harmful outcomes can arise when agents fulfill benign u…

A memory that reproduces every current prediction may still have forgotten how to learn from the next observation. We characterize this distinction for exact cumulative learning and attention. For smooth convex residual losses with unrestr…

This is a submission for the Kaggle Benchmarking Challenge TL;DR I asked 6 vision models to...

Many optimization problems provide direct access to only part of the gradient, while the remaining component must be inferred from function evaluations. This structure arises in performative prediction, performative reinforcement learning,…

Google AI Overviews appeared on a far larger share of tracked branded searches during September 2026,...

Another Rule for Using AI Without Losing My Skills ...

We establish finite-sample guarantees for conditional diffusion models learned from data and implemented with finitely many denoising steps. Our approach aligns the score-training objective with the sampling grid, allowing statistical esti…

Generative molecular design typically relies on over-generation and post-hoc filtering. Inference-time steering methods like Feynman-Kac (FK) steering improve efficiency by biasing trajectories toward high-reward candidates, yet they optim…

Time-aware facts, an entity graph measured honestly, and three bugs I only found because strangers read my posts.

This is a submission for the Kaggle Benchmarking Challenge Last weekend I built a model to predict...

n8n appears to be exploring how end-to-end automation could reduce repetitive design work, but it has...

Routing 5% of hard tokens to a 32B model and keeping the rest on a 0.6B model looks great on paper, until standard serving engines spend 95.8% of the step redoing prefix matching. TokenRouter fixes the scheduler and hits up to 64x higher t…

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

Independent review. I ran both tools on my own accounts, free and paid, with no vendor-provided access or early access of any\u00a0kind.

Every time a RAG application answers a question, it may need to retrieve documents and make an LLM...

This is a submission for the Kaggle Benchmarking Challenge. I Benchmarked 3 LLMs on...

https://www.kaggle.com/competitions/arc-prize-2026-arc-agi-2/leaderboard

https://www.kaggle.com/competitions/arc-prize-2026-arc-agi-3/leaderboard

"Will AI replace developers?" is the wrong question. The better one is: how should we change the way...

https://learn.chatgpt.com/docs/windows/windows-sandbox

Until 2026-09-15 our agent could end a run by asking its owner "can I leave this for next time?". It...

Most teams trying to understand AI search start by querying ChatGPT. There's a cheaper signal sitting...

I run a competitor-research agent: give it a company URL and it finds and verifies that company's...

MCP servers look harmless because they expose tools, not endpoints. A client calls a tool and gets a...

In 2022, I spent about a year applying for more than 2,200 jobs. I got two interviews. Two. After...

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

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

I spent a month defending a supervisor architecture I knew was failing. The symptoms were subtle at...

TL;DR LMCache is a caching layer for large language model servers that keeps the...

If you’re like me, you generate a lot of markdown files with your agents. Maybe they’re things like...

Sending an HL7 v2 message is easy. Open a TCP socket, wrap the message in MLLP framing, write it, and...

I assumed that if search found the right document, that was good enough for a conversational...

What already works with Microsoft 365, what is still missing for a company-wide rollout, and the pilot checklist I use.

This is a submission for the Kaggle Benchmarking Challenge I gave 39 language models the same...

I first noticed something missing while reviewing saved discussions of Microsonya, my Telegram...

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

An open-weight tabular model forecasts your last spring frost and a local Gemma writes the planting advice. Fully offline, no account, $0 to run.