Opportunities

Tool-using LLM agents are mostly evaluated assuming all tools work. When a tool times out, returns a week-stale value, or has its description poisoned in deploy

Large language models (LLMs) often produce homogeneous outputs, raising concerns that AI coding assistants may lead to convergence in the software artifacts tha

In quantum programs, Bugs4Q is a widely used benchmark containing real quantum defects. However, its evaluation assumes that benchmark labels remain valid and t

Feedback-driven loops support iterative improvement in large language models, reinforcement learning, and autonomous discovery, yet their gains often diminish u

Knowledge graph question generation (KGQG) aims to generate natural-language questions from structured graph evidence. Existing KGQG benchmarks, however, are mo

Existing architectural simulators expose aggregate metrics or raw traces, but fail to reveal complex interactions among microarchitectural events and their rela

skill.md files that stop your AI from building slop

Show HN: Open-source AI app builder you can embed into your own SaaS

Your gentle AI companion for a blooming pregnancy journey.

Vibe-Research: Your Personal Trading Research Agent · A股/美股/港股 的个人投研 Agent：每日复盘、资讯雷达、个股数据、板块中心、我的持仓、研究记录。Vibe-Research 把数据和功能配齐，由你自己的 AI 驱动投资研究。

「說人話」：繁體中文的去 AI 味改寫 skill。抓 38 種 AI 寫作痕跡，順手校正中國用語與半形標點，給 Claude Code / Codex / Cursor 用。

Tradingview MCP server for controlling Tradingview Desktop from Claude Code via Chrome DevTools Protocol

和你的 AI 一起玩的双人棋盘小游戏 · 18+ （A two-player board game you play with your AI — dice, tiles, spicy tasks, all run by code (18+））

UXON is an MCP server and API that lets AI agents and developers create landing pages, run A/B experiments, and track conversions across domains.

A memory layer for Claude Code that learns as you work. Persistent, per-context memory as plain markdown in your own git repo. No server, no telemetry.

Give your AI assistant a phone — OpenClaw plugin for real phone calls via Twilio + OpenAI Realtime, with in-call tools, transcripts, and call screening

Temporal Knowledge Graph (TKG) reasoning under the extrapolation setting focuses on forecasting future time-stamped events (facts) from historical data in a tem

Channel foundation models (CFMs) are developing rapidly, with recent studies reporting benefits from pretraining across downstream wireless tasks. Yet CFMs are

Context engineering has become central to building reliable AI agents, yet it remains largely unmeasured. Agents do not fail in isolation: their behavior is sha

CPUs are the most universal target for on-device LLM inference, but existing low-bit quantization methods offer either coarse operating points or fine-grained m