AI Intelligence Archive

Last month I spent 30 days letting AI write 100% of my code — a real SaaS, in production, no line of...

I built two A2A agents, made them discover and talk to each other, and documented every bug on the way.

The Telegraf Down alerts started piling up on a Thursday morning, and at first glance it looked bad....

Last month I wrote about how I use coding agents to build things. This week I pointed the same setup...

It is funny how things work out. You can let AI tools try to fix a code problem for days, but nothing...

Summary: I ran a Claude agent with only browser tools (no pre-written scraper code) against 60...

The bar was a slope: keep converting extra data into accuracy after exact-context statistics saturate. A full hierarchical Pitman-Yor model with Gibbs sweeps and inferred discounts moved the intercept and left the slope alone, halving with…

We cut our agent's CLAUDE.md from 548KB to 33KB on 2026-08-18 and put a 45KB cap on it. Eighteen...

Three articles ago I wrote that "endogeneity" was the deepest of the three critiques a...

The Demo Was Perfect I've done this more times than I'd like to admit. Build an LLM app....

I am building a site whose entire job is to be quoted by AI assistants. It is the marketing site for...

Last week I published a post about nine measurement bugs I found in my own evaluation harness, all of...

Anthropic surveyed 132 of its own engineers about Claude Code. Merged pull requests per day rose 67...

TL;DR If you /exit a claude --worktree <name> session with no uncommitted changes...

Long Story Short After using tools like Playwright MCP that can return large tool...

Frontier LLMs excel at textbook code but fail in production. Here is how Synthetic Scars and biological pain give autonomous coding agents real wisdom.

AI coding tools have become ridiculously good...guess we can all agree. You can describe an...

Parlotype's UI was English-only, with the copy baked into markup and C#: 211 literal attributes...

An AI team that never gets tired also never gets embarrassed. What three months of running an AI orchestra on a production codebase actually taught me.

If you've tried to point a local model — Qwen, a quantized Llama, whatever fits on your GPU — at a...

In 2026, AI agents have become the default paradigm for automating complex workflows: DevOps...

Hello, I'm Shrijith Venkatramana, and I'm building LiveReview — a blast-radius aware AI code review...

I can make almost any agent change look good with one carefully chosen prompt. Run it once. Watch...

I released mohdel 1.0.0 this week. It is a self-hosted LLM gateway and SDK for Node, MIT licensed,...

Compositional generalisation has been divided into lexical and structural generalisation. Previous work has found that structural generalisation is harder than lexical for Transformers. We propose that this difference is not inherent to Tr…

Post-training attention sparsification reduces the quadratic cumulative attention cost of pretrained Transformers by selecting a small set of context units (tokens or blocks) for each query. Existing trainable methods usually use a lightwe…

Frontier language models are more aggressively using subquadratic attention to reduce the memory footprint and compute requirements during inference while still delivering frontier accuracy. While existing systems make dense attention-cent…

Accurate prediction of equity returns remains a major challenge in computational finance due to the non-stationary, nonlinear, and low signal-to-noise ratio nature of financial time series. This paper proposes a hybrid two-stage architectu…

Dance-to-music (D2M) generation aims to synthesize music that is rhythmically and stylistically aligned with dance videos. A key challenge arises from the semantic mismatch between sparse dance cues, such as rhythm and style, and the dense…

Full-duplex evaluation often emphasizes whether an agent keeps speaking or stops. That binary cannot express a third response humans use routinely: continuing to speak while incorporating what the listener just contributed. The contributio…

When providing forecasted probabilities with a predictive model, the ideal model offers perfect calibration: the true probability of the outcome (i.e., the probability that $Y=1$) exactly matches the forecasted probability $f(X)$. In pract…

In urban search and rescue, articulated tracked robots (ATRs) must traverse structured but contact-rich environments such as stairwells and cluttered building interiors. Reliable autonomy remains challenging because robot-terrain interacti…

Agentic systems offer a promising way to automate embodied benchmark construction, but existing approaches typically cover isolated stages or remain specialized to predefined environments and task families. More importantly, multi-step con…

Conversational voice agents have advanced significantly, offering increasingly natural human-machine interactions through both cascaded and end-to-end architectures. However, while recent benchmarks extensively evaluate dyadic interactions…

Recent breakthroughs in LLM-based systems and their abilities in problem solving and coding have allowed progress in the AI for Science paradigm, potentially replacing human roles in machine learning (ML) research. However, while several f…

Fine-grained control of language model behaviors (e.g., steering) is among the more actionable outcomes of interpretability research. For binary concepts such as refusal, a single direction in activation space often suffices for steering. …

Enterprise Digital Twins (EDTs) promise data-driven decision support at organizational scale, but realizing them requires navigating siloed departments, tacit knowledge, and high-stakes decisions with long-horizon consequences. Existing ap…