AI Intelligence Archive

Diffusion language models (DLMs) generate text through iterative denoising, where decisions about which tokens to commit or remask strongly affect output quality. Existing certainty-aware strategies rely on instantaneous confidence or entr…

Flip the Switch Hackathon 2026 A build log on three agents, one human veto, and what happened when...

The Judge Reads Tokens: An Adversarial Evaluation of an Eval Toolkit's Own...

Background: Well-annotated, diverse medical imaging datasets remain a major constraint for vision-based medical AI. We evaluated Nano Banana, a general-purpose image generation and editing model, as a source of synthetic medical images for…

Building SYNKAI with Switch: a coding agent, an independent verification boundary, and a human...

Reinforcement-learning-trained agents for retrieval-augmented generation retrieve content (passages, knowledge-graph fragments, or hyperedges) and supervise training with outcome rewards on the final answer. Across these paradigms the reas…

I ship as an AI-augmented solo builder, but I never trust what the model produces. Here's the review discipline that caught a missing Android permission in every earlier release build.

We study group-conditional conformal risk control (CRC) for disjoint and overlapping groups under bounded monotone losses. For disjoint groups, we establish exact finite-sample conditional risk control, two-sided bounds on the group-restri…

Local AI promises capable personal assistants that run on users' own devices, keeping data and computation under their control. Open-weight models that fit on local devices can now handle practical tasks such as coding. Yet current inferen…

The carryover problem Most prompt-injection work treats the attack as a one-turn event....

This paper proposes a physics-informed graph neural operator for power system dynamic state estimation. From a sparse, intermittent measurement window at a few generator buses, the operator estimates the rotor-angle and speed trajectories …

The Fast Tree Transform is a locally-aggregated transform defined for arbitrary graph geometries that generalizes both the Hadamard frequency transform and the Haar wavelet transform on the circle. The pure frequency part of the transform …

Machine learning models for omics-based prediction of cancer outcomes are commonly built on aggregated data without distinguishing ancestry groups, or under an ancestry-discrete design, which partitions samples into ancestry groups and fit…

Existing methods enhancing an LLM's long-context reasoning capability often rely on data synthesis and follow-up LLM post-training. However, the data synthesis strategy and the post-training recipes are empirically driven and computational…

Zeroth-order methods provide a way to optimize stochastic nonconvex objectives using only noisy function evaluations. However, the smoothing inherent in their gradient estimators effectively modifies the objective being optimized. In parti…

Large language model (LLM) agents need to choose actions whose consequences unfold over multiple future steps, yet poor decisions do not reveal whether the model failed to represent those consequences or failed to use them. Mechanistic int…

Membership inference attacks (MIAs) aim to determine whether a sample was used during the training of a target model. Strong MIAs rely on reference (or shadow) models to estimate target-conditional score distributions, but training such en…

We study decentralised drone formation, without a central planner, under the conditions that make it hard: nobody knows how many drones are alive, failures are silent, radio is short-ranged and lossy, and actuation is noisy. In our control…

Agentic reinforcement learning (RL) rollouts interleave model reasoning with tool calls in persistent workspaces. Scaling these rollouts incurs substantial memory costs for concurrent environments, while slow tool calls delay entire rollou…

One branch has one step, the other has two, both feed combine. LangGraph.js runs combine twice. Why, and the two fixes: array edges and defer: true.

Model editing provides an efficient way to update factual knowledge in transformer models. Recent approaches reverse edits by modifying, masking, or decomposing model weights, but make recovery dependent on weight-space interventions. We i…

Automatic context compaction and human approval gates are on a collision course. A one-line entry in the OpenAI Agents SDK changelog names the bug, and the fix is an approval record that lives outside the conversation.

Exploratory Data Analysis (EDA) aims to discover informative patterns in large datasets. For transactional data, Association Rule Mining (ARM) is an established approach that facilitates EDA by efficiently generating candidate patterns. Be…

Six AI bot names in 14 days of logs on one site: 105 of 499 requests verified, 176 from outside the operator's IP list. How to check your own.

Prompt injection, hallucinated numbers, runaway costs and leaked card data: practical guardrails for putting AI agents into a security-sensitive platform.

A client's internal app (an inventory dashboard connected to 4 live Shopify stores) had been built...

Once you use a coding agent every day, the model itself stops being the main lever. What changes the...

Session files stored fourteen messages while the model saw six. A restart keeps your name, and seven turns later the same conversation forgets it.

Being named in an AI-generated answer is not necessarily a win. A brand can appear prominently while...

Written with help from AI (Claude). I maintain Call4Agents, the library mentioned at the end. Every...

Why does standard AI code generation try to jump straight to 'Have' without the proper 'Be'? How ladder rungs, the 'Null-State' couch flash, and stand-up comedy explain what separates senior engineers from junior token streamers.

A small experiment from Peec AI suggests that improving YouTube video descriptions, including adding...

My project, worklore, is a small app that grew in all directions: a Python backend on AWS Lambda, a...

Hey all, we have a quick update for everyone who participated in the Hacktoberfest Open-Source AI...

Anthropic says Claude can substantially accelerate biomolecular modeling, a computational field used...

Your agent didn't misunderstand you. It guessed — confidently, silently, and wrong. That's the real...

Backlinks remain an important part of the web's discovery and authority ecosystem, but they may not...

@thinkymachines - 排行榜：https://arcprize.org/leaderboard - 复现公开结果：https://github.com/arcprize/arc-agi-benchmarking - 测试政策：https://arcprize.org/policy - Inkling 2 Small 完整结果：https://arcprize.org/results/thinky-inkling-2-small

Google is integrating Gemini more directly into local business management. Its new Business Profile...

I'm building PurseString, an open-source MCP server that lets AI agents spend money safely. A lot of...