AI Intelligence Archive

Multiple SEO practitioners reported unusual Google Search Console (GSC) click spikes between October...

This is a submission for the MLH x DEV Writing Challenge What I Built Every crash gets a...

Before you install a Claude Code skill, open its folder and look for a scripts/ directory. If the...

Disaggregated flash looks cheaper per terabyte until a job restarts and a hundred GPUs wait on a shared write path that was sized for steady state.

Sparse expert models buy FLOPs back, then spend them on all-to-all traffic, expert imbalance and a batch size that never quite fills every expert.

OpenAI has expanded Daybreak into two controlled-access tiers for authorized cybersecurity work:...

User embeddings are central components of modern recommendation, personalization, and behavioral modeling systems. Though these embeddings can compactly encode rich behavioral information, they are inherently dense and opaque, limiting int…

LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining high-scoring methods. However, the process is often slow because the LLM generate…

AI-Scientists arrived, but a world for them to grow in did not. Human scientists take theirs for granted $-$ centuries of open problems and shared ideas, waiting in the scientific literature. To AI-Scientists, that world is readable but no…

ML code should run where researchers choose, not where it was first written. Today, machine learning code mainly lives in two ecosystems, PyTorch on NVIDIA GPUs and JAX on Google TPUs. Migrating repositories between them means building and…

Interpretability, AI auditing and assessments of machine consciousness increasingly rest on mechanism-level quantities: functionals of a system's causal transition law that describe how it computes, not what it outputs. Experiments see tha…

To interpret a direction in a language model's residual stream, we can look for text that strongly activates it. But when such text is found by scanning a corpus, it is limited to what that corpus contains. We develop Maximally-Activating …

Adversarial Training (AT) is an important method for improving model robustness. We study the dynamics of deterministic Gradient Descent (GD) in AT. Most existing works in this direction focus on the small or vanishing step sizes regime, w…

On-policy distillation (OPD) trains a student on its own rollouts under a frozen teacher's per-token supervision. Does this dense signal reduce the training FLOPs needed to reach a target accuracy compared with reinforcement learning? We s…

Reproducing machine learning experiments requires reconstructing procedures from information scattered across papers, released code, and supporting artifacts. For coding agents, reproduction success can therefore depend on their ability to…

Claude Code Hooks: A Complete Guide to Automating Your AI Coding Workflow If you've been...

Coding with agents turned my job into one infinite loop of asking, reviewing and approving. I lost the fun part of solving problems. Here's what I got back.

The run said success. The dashboard showed three findings. The report read like a careful security...

A defender anticipating an attacker needs a probability distribution over the attacker's next action from information available before that action occurs. Two structures complicate this: the attacker's behavioral regime persists and can sw…

Slashing AI Agent LLM Bills by 75%: Sub-Millisecond Context Compression and Semantic Prompt...

Typed-decision models score options that the caller supplies at request time, so their accuracy depends on label wording that the model's developer does not control. We compare two releases of a 307M-parameter multilingual cross-encoder, R…

Neural networks are likely to be among the most consequential artefacts in human history. As these systems become more capable and autonomous, their potential to cause societal harm also grows, making AI safety one of the defining challeng…

LLM-based medical assistants that follow a patient across visits need a memory that keeps the patient's clinical state correct as it changes. We examine the errors of five memory systems on longitudinal medical dialogue and find three recu…

Chat remains the default surface for many large language model (LLM) tasks, even as agentic tools such as OpenCode excel at coding and automation. Yet the model sees the current dialogue but not the workspace around it. We explore meta acc…

Vision-Language-Action models (VLAs) enable general-purpose embodied intelligence, but their performance is brittle under distribution shift, where unanticipated failures can damage equipment or endanger people. Deploying VLAs in real-worl…

Discovering continuous symmetries directly from differential-equation data can reveal geometric structure for model reduction and scientific machine learning without symbolic determining equations or a closed-form representation of the gov…

Molecular representations such as fingerprints and learned embeddings play a central role in cheminformatics and small-molecule machine learning. They serve as the primary input for a diverse array of tasks, including clustering, dataset s…

Coding agents are among the most economically consequential deployments of LLMs to date, making reliable evaluation increasingly important. Yet even benchmarks that are carefully validated at release can become stale. As models improve, th…

Low-rank adaptation (LoRA) is commonly used in both supervised fine-tuning (SFT) and reinforcement learning (RL), often under similar optimizer settings. Yet, how the different dynamics of the two stages manifest in the low-rank increment …

The growing use of AI in mathematics raises a question: can we detect AI involvement in proofs, separately from AI assistance with writing? Historical arXiv papers, recent papers disclosing substantive AI use, and manuscripts released by O…

Note This is a shortened version of the original writing on kig.re — my personal blog. Here is...

Run untrusted LLM-generated code in a hardware-isolated sandbox with the network locked to an...

I build practice exams for Dutch certification exams: the VCA safety certificate, the hospitality...

When Claude Code ignores a rule, the usual move is to reword it. Start with the verb, use backticks...

AI agents are getting real tools: email, payments, code repos, customer data. At the same time, they...

#HowISwitch · Flip the Switch hackathon Here's an incident every Nigerian developer who has touched...

Description: Perfect recall is dangerous without discrimination. How one agent stores the signal that...

Description: Agent memory is only useful if every claim traces back to a real incident. A practical...

AQuA is an open-source quality agent that surfaces the production failures your health checks miss and, when you ask, traces a failure to the line of code behind it. Try its dashboard locally.

Description: An on-call SRE agent is only as good as the incidents it can recall. Structured...