AI Intelligence Archive

As sequence lengths continue to grow, distributed attention based on sequence parallel (e.g., Ring-Attention) has become a mainstream solution for large language models (LLMs). Nevertheless, inherent communication dependencies limit comput…

KV cache eviction is not merely a token-ranking problem: the workspace retained for generating eviction queries also determines the quality of those queries. Consequently, an early workspace error can distort later query observations and r…

Developers insert logging statements in source code to record its execution, and the resulting logs are essential for detecting and troubleshooting system anomalies. A key part of these statements is the log level (e.g., DEBUG, INFO, WARN,…

Fifteen days, twenty-five releases. PageSift went public as 0.20 on October 20; today it ships...

What 586 Real Traces Taught Us About LLM Agent Determinism How temperature selectively...

Forecasting emotion in conversation is increasingly framed as predicting the next emotional state's value. We show this targets a hard quantity in a state-observed testbed and propose a learnable, deployable reformulation instead. On valen…

Comparisons in conversational emotion-shift forecasting are easily distorted when a learned model receives rich features but its transition baseline is given a noisy or unavailable current-emotion label, when hyperparameter budgets differ,…

Recycling a target model's own predictions offers a training-free source of proposals for speculative decoding. In vision-language models, however, existing recycling indexes predictions by the last token alone, conflating predictions comp…

The fastest way I know to break a working LLM feature is to "just tweak the prompt" on a Friday....

Agent skills are just markdown files that an LLM will obey. Here's what malicious ones look like, how they were caught with a static analyzer, and why the MCP config file is the most dangerous line that never reaches the model.

An agent can successfully query a database and still give you the wrong answer. Ask, “How many...

Unattended LLM pipelines fail in ways a person would normally fix by editing the prompt. If the...

Notes from building ContaCal, a photo-based calorie logger for Brazilian meals. The pipeline, the hard parts (regional dishes, portions, lunchboxes) and the limits we tell users about.

Apliquei as fases do Spec Kit em uma tarefa de um projeto de previsão do Brasileirão e conferi o resultado contra a própria spec.

A team I talked to last month had a 4x jump in inference spend over one quarter. Not a crisis — they...

A Postman desktop update added its plugin to Claude Code and Codex for an existing user. Its installer is built to approve its own Codex hook. How to check.

If you've debugged a web app with an AI assistant, you know the loop: The AI asks what the console...

A personal assistant is easy to demo and hard to trust. The demo ends when the assistant answers....

This is part of my build-in-public series on running LLM workflows in n8n in production. Everything...

If you let Claude Code, Codex or Cursor drive a browser, a big part of your token bill is page...

Chunk, embed, store, retrieve, rerank and answer with citations: a complete RAG walkthrough on Pinecone's new document indexes and the Claude Messages API.

A tour of the A2A CLI against Rust agents on A2A v1.0: the official Rust SDK, a plain stdin/stdout program wrapped by a2a server --exec, and an ADK coordinator on Gemini, each timed from the CLI and from a Rust client.

A tool call has passed the gate and is running. Now the role is revoked. Does it stop, or does it...

I merged two PRs to fix my dependency alerts on GitHub. Both had empty diffs. GitHub kept showing 11...

A few weeks ago I put a small API online that agents pay per call with x402, USDC on Base. It scans...

OpenAI says ChatGPT’s web-search-like query volume is roughly 20% of Google’s traditional search...

In August I ran a controlled experiment on my open-source multi-agent pipeline: the same task, done...

While my AI agent was reading a web page, the page tried to give it orders. The page started with...

How I Overhauled DocsGPT's Ingestion Engine & Supercharged RAG Context: My Hacktoberfest 2026...

I spent the Flip the Switch hackathon building Shield, an agent that checks a daily table, explains...

Hacktoberfest 2026 wrapped up on October 31st! Thank you to everyone who built, hosted, mentored,...

Switching AI character chat apps is common: features change, free tiers shrink, rules shift, or...

Agent TUIs can put the terminal in raw mode, so Ctrl+C arrives as byte 0x03, not SIGINT. Here's what that means for Esc, exit and the tests they spawn.

Anthropic has introduced FlashProve, an open-source research prototype designed to cryptographically...

A few years ago, creating automated tests was one of the biggest bottlenecks in software...

How my workflow evolved from solo prompting in AI Studio to managing a multi-model AI team, running...

Wikipedia dropped this UUID in 2014. Now it's everywhere ...

An AI response arrives as text deltas. A Markdown renderer normally receives a document. Connecting...

Claude Code and Codex log every session to JSONL on your disk. Eight jq commands pull out the shell commands, edits, errors, denials, slow calls and model.

Learning a universal action representation from video requires modeling dynamics that are consistent across different executions of the same action yet invariant to changes in embodiment and appearance. Existing latent action models infer …