AI Intelligence Archive

Agents drift when the model alias updates, a prompt gets edited in a dashboard, or a tool schema changes underneath them. Ship all of it as one versioned manifest.

Why host auto-compaction silently lobotomizes long-running AI coding sessions, and how 1983 SysV init.d runlevel files, Memento tattoos, and fork/wait subagents let our orchestrator survive two 230k-token compactions mid-ticket with zero l…

My Claude Code and Codex sessions often run 30 to 60 minutes, and there's no good way to show someone...

I put design direction and review for blog pages, app UI and Shorts into one skill that Claude Code, Codex and agy load from the same directory on my machine. The checks prove installation and explicit invocation on synthetic cases, not de…

Anthropic has committed to publishing regular reports on what it learns about model behavior and...

How do we know code is correct, and what role does human code review play in knowing it?

I first heard about NUMMI years ago on an episode of This American Life. Toyota took over one of...

AI coding agents reliably turn flaky tests into weak assertions. The failure isn't the flake; it's that nobody reviews the diff that deletes the boundary.

In April 2025, Shopify CEO Tobi Lütke posted an internal memo publicly. The line everyone quoted:...

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

在 Luma 中试试 Product Shots - https://app.lumalabs.ai/solutions/product-shots?utm_source=tiktok&utm_medium=p-social&utm_campaign=q4-social&utm_content=productshots&utm_aud=plg

Where the spending rules live: agent authorization on AWS vs Sui A bot that can pay you...

Anthropic's Claude computer use API, released in October 2024, takes a screenshot, decides where to...

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

I put ten AI agents on trial inside a fake company, hid the rules where real rules live, and let the...

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

https://openrouter.ai/apps/codex

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

We just wrapped the very first month of the MLH x DEV Writing Challenge, our new way of celebrating...

Welcome to Singularity News ... until ... well, we all know when! This is the first community-based...

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

When AI agents act on behalf of users, traditional audit logs often don't tell the full story of who...

Hello, I'm Maneshwar, and I'm building LiveReview — a blast-radius aware AI code review built for...

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

Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requires specialist linguistic or scientific knowledge. We used the Wikipedia Game to test …

Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Concept-based attribution methods interpret models using human-understandable concepts. Existing concept-based methods can on…

Hello, I'm Rijul, and I'm building LiveReview — a blast-radius aware AI code review built for your...

The expressivity of a neural network $Φ$ describes the class of functions that a network can express. The term topological expressivity refers to a family of measures particularly suited to understand binary classification and is often for…

Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities can be elicited. We show this assumption does not hold under adversarial conditions…

This is a submission for the Kaggle Benchmarking Challenge. This would probably needs its own...

A parallel sampler can choose at random which coordinates to generate together. For a target $p$ and the output law $q_U$ of a schedule $U$ drawn afresh for each output, we compare the schedule-averaged divergence $\mathbb{E}_U D_{\mathrm{…

Deep-space communications operate under intermittent connectivity, long propagation delays, and relay storage constraints. In such networks, the Bundle Protocol enables store-carry-forward communication, requiring relay nodes to manage lim…

Clinical sleep medicine repeatedly documents profound divergences between objective sleep duration and subjective daytime impairment, notably exemplified by sleep state misperception in paradoxical insomnia and boundary instability in narc…

A central challenge in de novo protein design is generating proteins with desired structural and functional properties. Existing design models typically require a dedicated input representation for each property, limiting the design object…

Qwen3.8-27B, 600 steps, 12 reward channels: CISPO, REPO-R and prompt filtering lifted holdout from −0.47 to +1.80, and an advantage floor silently zeroed 96% of the signal.

Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model predictions may become unreliable as policies evolve. We introduce RSI-Anything, a doma…

Vision-Language Models (VLMs) increasingly analyze and reason about images, yet it remains unclear whether their internal representations faithfully encode the structured relations required for such reasoning. We introduce EICS (Evaluation…

While deep learning models for tabular data have recently received significant research attention, the choice of objective functions for regression tasks remains an understudied degree of freedom. Several lines of research offer alternativ…

We study the last iterate of standard asynchronous Q-learning from a single trajectory of a finite Markov decision process. The trajectory follows a fixed behavior policy whose state--action chain is irreducible and may be periodic. For di…

Neural semantic parsers generate meaning representations token by token, yet well-formedness depends on references, scope, and graph relations that unfold during generation. Constrained decoding prevents locally invalid tokens but does not…