AI Intelligence Archive

Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering performance, yet existing work typically evaluates harnesses as monolithic systems, leaving the effectiveness of indivi…

World modeling enables intelligence to anticipate consequences, guide interventions, and learn from interaction. Yet predictive models remain domain-specific: can a common learning principle support world modeling across radically differen…

Generative models are increasingly used to solve scientific inverse problems, but existing evaluations still focus primarily on whether a method can produce a single plausible reconstruction. This is insufficient for ill-posed problems, wh…

Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy distillation (OPD) to supply dense token-level supervision from a self-teacher with privileged task sk…

Safety evaluations for large language models rely on surface-form classifiers that report declining harm scores across model generations. We provide evidence that this methodology is systematically incomplete: explicit discriminatory conte…

Action chunking is widely used for action generation and execution in Vision-Language-Action (VLA) policies, yet existing approaches commonly use a fixed action horizon. During a rollout, different task stages may require different levels …

Generative agents are increasingly used to select and narrate video highlights, but they typically operate over unstructured or frame-level representations. Their output is consequently difficult for a viewer to verify and steer toward ind…

Radio Frequency(RF)-Fingerprinting is a spectrum monitoring technique that identifies specific transmitters based on hardware impairments imprinted within the emitted signal. Although widely researched, studies almost exclusively consider …

World Action Models (WAMs) advance beyond conventional visuomotor policies by jointly predicting future world states and robot actions, enabling the policy to learn physical dynamics that support effective control. However, recent tactile …

That's a working React app. Sidebar navigation with active states, four KPI cards, two charts, and a...

Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as benchmark task types or conversation types in deployed agents. Exhaustive testing is expensive, so evaluation rests on a sample of labe…

i'm jon, i co-founded backboard.io. this is a launch post. it's short and there's code. video models...

TypeSafe's Jev is an odd one. It isn't a chat model - you send a state plus typed questions (Choice /...

I stored passwords in plaintext on a floppy disk in the 1980s. Recently, a coding agent made a...

Your Markdown can be perfectly rendered and completely wrong Markdown has an unfair...

Federal Reserve Chair Kevin Warsh singled out AI debt issuance as a driver behind the 10-year Treasury yield crossing 5 percent. Here is how the feedback loop works.

KAIST EvolveTrade shows that frozen LLM trading agents improve Sharpe ratio not by writing new strategies, but by letting policy refinement turn Python outputs into explicit allocation math.

Six weeks with the Pocket AI recorder: meeting action items, voice-memo idea capture, personal logistics, and its MCP server wired into Claude Code.

A read-only scanner that fingerprints MCP on both transports and sorts every endpoint into open, protected, or out of spec. Four postures, one...

I kept running into the same failure mode when switching between AI workers, browser sessions, or...

A $52 to $3,292 token-launch bot, an $89 to $7,769 six-agent trading desk, a stablecoin arbitrage, and two more. What on-chain data, fee schedules and the authors' own demos actually show.

Since August 2, 2026, Claude embeds a statistical watermark in its text output, and Anthropic's...

Most AI features don't fail in the model. They fail at the gate. Someone demos a shiny prompt....

It was a Tuesday morning. My OpenCode session had 378,755 tokens of context — weeks of trading-bot...

Semrush has published a focused study on a critical question for companies seeking visibility in...

Every week brings a fresh cycle of tech Twitter arguing whether Artificial General Intelligence (AGI)...

I burned a cloud IP address doing AI safety testing. Then I moved the whole operation onto a...

tldr; I asked Claude Fable (in plan mode) to screen record and create cool demo videos for my...

I recently faced an interesting challenge while managing a fleet of IoT devices in Kenya. Managing...

TL;DR Most AI agents re‑read transcripts instead of learning principles, so they repeat...

Every multi-tenant B2B SaaS platform I've worked on eventually converges on the same authorization...

Last week I gave an AI agent a simple job: look at a sales pipeline and tell me what it is worth. It...

I spent a day reading 45 platform terms of service end to end, because an agent I run kept failing at...

The symbiotic scaling of artificial intelligence models and high-performance computing systems continually creates algorithmic challenges in their convergence. Foundation models (FMs) are a crucial example, requiring months-long training o…

Characterizing the physical properties of clay and cementitious materials matters across many fields, from materials science to geological waste disposal. Property simulation typically calls for 3D imaging, which is expensive, not always a…

We study repeated contract design when a principal observes outcomes but not the actions that generate them. The principal may use any bounded outcome-contingent payment vector, and the agent's best response can make expected profit discon…

Large-scale routing often requires visiting clusters of nodes in a prescribed order, giving rise to the Ordered Clustered Traveling Salesman Problem (OCTSP). Optimizing each cluster independently seems natural, but misses non-local depende…

The Moat Machine: I Wrote About Product Strategy in 2022. In 2026 I Built the AI Plugin That...