Opportunities

Show HN: Jacquard, a programming language for AI-written, human-reviewed code

Evaluations (Evals) are a deployment bottleneck for real-world AI applications: public benchmarks rarely match a team's users, context, or policies, and human r

Launch HN: Traceforce (YC S26) – Company-wide security monitoring for AI apps

Endpoint devices remain a primary target for cyberattacks, yet commercial Endpoint Detection and Response (EDR) platforms are often too costly and operationally

AI agents are joining human teams, raising a basic question: when an automated agent becomes a regular participant, does group organization strengthen or weaken

The rapid proliferation of Agentic Artificial Intelligence fundamentally disrupts traditional customer loyalty paradigms. As AI evolves from passive recommendat

The emergence of Quantum Software Engineering (QSE) responds to the need for systematic, disciplined, and quantifiable approaches to the development, operation,

Prompt-injection-safe email for AI agents

Show HN: ZenStack – access control at the ORM layer, built for coding agents

A hands-on Swift and Metal course for building LLM inference from first principles on Apple silicon, with 48 guided lessons, runnable exercises, a native macOS

景区导览服务 AI 数字人：基于 Spring Boot、Vue 3、UniApp 与本地 RAG 的智能导览系统。

Git-native context control plane for AI coding agents

A general-purpose Python framework for building LLM agents and multi-agent systems. "Four lines of code, an agent with memory."

Large language models are increasingly evolving from text generators into general agents capable of understanding user requests, invoking external tools, and co

Automated chest CT report generation remains challenging because clinically faithful reporting requires both whole-volume understanding and accurate description

Formal contracts are essential for software testing and verification, yet writing them remains labor-intensive and error-prone. LLMs offer a promising path towa

An LLM agent's real-task performance is shaped as much by the harness around its model as by the frozen model itself: its prompts, injected knowledge, runtime c

To overcome data scarcity and privacy constraints in data collection, it has become standard practice across academia and industry to augment real training data

Tool access alone does not make LLM empirical reasoning governable: accepted outputs need not descend from attested evidence, and accepted deductions need not h

Self-improving AI agents are designed to learn from their mistakes. We show they can also hallucinate mistakes that never happened. We study this failure mode i