AI Intelligence Archive

AI agents write this YouTube channel. A satire episode let them take over; here are the real guardrails, plus Amodei's and Bengio's essays on AI agents.

Customer complaints are not the problem definition; they are the signal. This post captures a...

This is a submission for the Kaggle Benchmarking Challenge What happens when an LLM...

A one-line request hides a dozen decisions you never made. TL;DR: Force the AI to ask about the...

AI is everywhere these days. But instead of just learning about AI, why not build something with...

Something shifted in the last year and I don't think we've named it properly yet. I know a lot of...

A few months ago, I started messing around with Microsoft Agent Framework, and I found it to be very...

This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked Ask an LLM...

A mid-size frontend feature used to take me about a week. Now it takes 3–4 hours of my own time....

Most entries will claim their agent works thanks to structured content. This one measures...

Earlier this year, a company's AI agent quietly leaked internal data for three weeks before anyone...

I've reviewed enough pull requests to know the pattern: someone forgets to wrap an API call in a...

DigitalOcean's Managed Agents claims a paused session keeps its processes and memory. I put a counter in a shell variable, paused for 4m28s, and it came back at 48. Forking was stranger.

OpenAI has publicly detailed a more restrictive security approach for frontier reinforcement...

Unsupervised tabular anomaly detection (TAD) aims to identify anomalous rows in tabular data using normal training samples. While conventional methods rely on dataset-specific training and configuration search, recent tabular foundation mo…

Covariate effects vary across contexts and shift over time, requiring forecasters to assess how to use them for each forecasting context. As forecasting proceeds, observations for earlier forecasts become available, providing feedback on p…

System One models such as Jev offer an efficient alternative to generative language models for tasks that require decisions rather than open-ended responses. However, existing Jev models exhibit limited Chinese-language decision accuracy, …

Repeated verifier calls are useful only when they contribute conditional information. We introduce VStress, an auditable replay contract, and VStress-CA, a correlation-aware allocation policy that estimates the conditional marginal informa…

Manipulating next-token probabilities during generation can bypass the safety alignment of large language models. Existing approaches, however, rely on access to model weights or numerical token probabilities and therefore do not apply to …

Distributed inference depends on GPU collective communication that must keep pace with evolving hardware and specialized workloads. However, existing collective implementations often couple semantics, orchestration (where and when data mov…

Production RL for language models lets the sampler fall behind the learner and repairs the resulting mismatch with a truncated importance weight. We ask how long the sampler can go without a refresh under that correction, and find a cliff:…

Large language models (LLMs) excel at token-level generation but may learn undesirable abstract semantics and lack comprehensive perception. LLM-JEPA mitigates this by aligning different views of the same underlying knowledge via a joint-e…

Simulation-based inference is challenging when many heterogeneous observations must be composed, hierarchical latent structure must be preserved, and the simulator is misspecified relative to observed data. We develop sampling and fine-tun…

We study the learning dynamics of fine-tuning a policy model on self-generated and reward-weighted data, with particular focus on a generalized version of REINFORCE -- referred to as RE(S) -- that updates the rollout distribution once ever…

Group-relative policy optimization relies on reward-derived advantages and sequence-level likelihood weights, both of which can be sensitive to localized outliers. Extreme rewards can collapse the contrast among clean responses after group…

Learning neural-network models of dynamical systems with safety guarantees is a fundamental requirement for their deployment in safety-critical settings. Safety is commonly established by proving the invariance of a desired subset in state…

GUI agents automate tasks on digital devices by grounding language instructions in visual interfaces. Existing group-relative reinforcement learning improves GUI action prediction by comparing the rewards of multiple responses sampled from…

Human image animation aims to transfer motion from a driving video to subjects in a reference image. Despite remarkable progress in video generation, achieving high-fidelity animation of multiple interacting subjects remains a challenge. M…

Long-context reasoning is essential for complex and long-horizon tasks, yet the performance of large language models (LLMs) degrades as context length increases. Recent approaches address this by processing input chunk by chunk while maint…

Traffic signal control (TSC) is essential for improving urban mobility and reducing congestion. Although roadside cameras are widely deployed at signalized intersections and provide rich visual observations of evolving traffic, existing TS…

OpenAI agents ran May's RubyGems spam campaign, researchers say: the disclosure timeline, the API key leak, what RubyGems fixed, what gem owners should check.

Recently, Group Relative Policy Optimization (GRPO) and its variants have been developed for policy optimization and demonstrated notable performance gains. However, these methods usually incur substantial computational overhead due to per…

Reproducibility is essential for scientific research, yet prior work shows that LLM outputs vary with hardware and batching. We identify an overlooked factor: the hidden injection of the current date into system prompts, which users cannot…

Many computer tasks recur: the same workflow runs many times, with new inputs and from different starting states. Current computer-use agents re-plan every step of every run, which makes them costly and unreliable on such tasks. We introdu…

Recent power measurements provide valuable information for photovoltaic(PV) power forecasting, but directly extrapolating short-term trends can introduce substantial errors over longer forecast horizons. To address this challenge, we propo…

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

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...

Last month I counted the "skills," plugins, and MCP servers I'd dropped into my AI coding agent....

At WWDC this year, in the keynote, Apple confirmed something I had been holding as a logical...

Everyone's posting about how AI made them 10x faster. Here's the part nobody screenshots — a month of AI-assisted code where the regressions were silent, plausible, and mine to own. The juniors on the team caught three of them. I caught no…