AI Intelligence Archive

Recently, I've been struggling more and more with the way we're using AI to automate nearly every...

I got tired of wondering whether anything I read online was written by a person. So I built...

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

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

You ask your AI assistant for a quick script. It writes clean code, imports a package you've never...

I spent three weeks trying to fix a planner-executor pipeline that was failing in a way I couldn't...

Pull one concrete build decision from each Chain of Thought episode in the agents collection, from context to memory, stacks, and coordination.

OpenAI has launched interactive learning visuals in ChatGPT, adding hands-on modules that let users...

A while ago I finished a piece of work I was proud of: a design system built the way I'd argue a...

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

How a raccoon in sunglasses (me) ended up running a Rick and Morty themed AI crew, a voice butler and a private search engine - all free, all on one CPU-only laptop.

When I started building Vicquant, the core design principle was simple and non-negotiable: the AI...

An open-source Agent Skill gives Claude, Gemini CLI and Codex a staged logo workflow, SVG checks and a searchable library of 1,400-plus marks.

Originally published at kotwal-itpro.github.io. A lot of teams now use AI models to read large piles...

Google's first Suncatcher satellite carries four TPUs. They survived radiation, but cooling in a vacuum is the real limit.

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

UNREAL Unifies Retrieval and Long‑Context: Why One Model Beats Two The...

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

I run a small software company by myself. Claude Code agents play the engineers, QA, marketing and so...

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

As we move through the world and carry out everyday tasks, we encounter objects that may become relevant only later. We are capable of recalling where we left something or what was inside a container, even without knowing we would need it …

Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkpoints. A key promise of RLVR is the discovery of new reasoning strategies. In principle, a model can sample novel ideas ab…

Conditional memory architectures such as DeepSeek Engram use input n-grams to look up learned embeddings, expanding the capacity of large language models (LLMs) with limited additional computation. Beyond model scaling, this architecture h…

Real-time robot control demands enough visual history to infer motion and task progress, but processing that history can delay action. We present Long-WAM, a model-system framework for scaling the context of causal world-action models unde…

Heavy-tailed noise has been widely observed in modern machine learning, motivating the use of methods like gradient clipping and normalization. While these methods are well understood in centralized settings, much less is known in decentra…

Vision-language-action models (VLAs) are strikingly sensitive to instruction phrasing and do not inherit the language robustness of the vision-language models they are built on. A one-word edit can move success by tens of points: $π_{0.5}$…

GNN-to-MLP distillation aims to retain the predictive accuracy of a message-passing teacher while deploying a graph-free MLP at inference. Existing methods mainly transfer node-wise predictions or use confidence-based reweighting, but they…

Machine unlearning asks for a deletion algorithm whose output is close to retraining from scratch without the selected forget examples. In this work, we study forget-only unlearning, where the deletion algorithm receives only the trained m…

Latent world models have shown a remarkable ability to predict future states and to plan in the real world. In practice, however, we lack a principled way to estimate how their capabilities scale with model size, data, and compute, an open…

Language-model agents are increasingly asked to carry out open-ended scientific research, yet their results are usually graded against a known answer, a rubric, or a language-model reviewer, none of which can tell whether a new scientific …

Prompted embedding models have recently received increasing attention, particularly for retrieval, where detailed retrieval instructions are provided as part of the retrieval prompt. Several new datasets and studies have examined this sett…

Large language models are increasingly applied to tasks grounded in long, heterogeneous information sources. Conventional Retrieval-Augmented Generation (RAG) relies on fixed similarity-based retrieval, while agentic variants adapt queries…

Many of the questions now put to large language models have no correct answer to score against: what a policy is worth, which option a user should choose, how to weigh competing values. Stated-preference economics has faced this problem fo…

Online learning is an attractive framework in many domains because it permits well-defined learning even when data are dependent or chosen adversarially. This generality, however, comes at a steep price, introducing significant statistical…

Robot foundation models provide strong visuomotor control, yet their performance can degrade when object positions or task instructions change. Further improvements often require post-training on substantial robot data, which can be costly…

Small tabular datasets with expert-designed spectral features are the norm in operational Earth observation, and the networks applied to them are typically hand-designed. We revisit one such published model -- a Sentinel-2 algal bloom clas…

I wrote a task for Terminal-Bench, a public benchmark of hard command-line tasks for AI agents. The...

We study the best arm identification problem in a stochastic environment with a novel form of adversarial perturbations, which we coin Shifting Means. While classically the mean rewards of the $K$ arms are stable in time, in Shifting Means…

Our MCP server's tool descriptions were full of instructions to the model. Anthropic's directory review doesn't allow that. Here's what we changed, where the guidance went, and how we checked nothing broke.

Sampling from a softmax distribution is a fundamental operation in machine learning, but its linear complexity in the number of items makes exact sampling impractical at scale. Two-level softmax (2LS) sampling is a popular alternative enab…