Tag
A researcher shares how AI has made brainstorming and prototyping ML research ideas much faster than they can actually test them, creating an overwhelming pipeline of candidate experiments, and asks others for advice on managing the bottleneck.
作者分享放弃用 ChatGPT 做严肃研究、转而将 100+ 技术论文迁入 Google NotebookLM 后的四条反直觉经验：限制开放网络可减少幻觉、跨源交叉验证优于线性阅读、文档需分层分类管理，以及 Audio Overviews 的意外价值。
A practitioner discusses concerns about sharing novel R&D ideas and trial data with cloud-hosted AI providers, asking how companies and researchers actually protect their IP and whether local/offline LLMs are a viable alternative despite being weaker and compute-heavy.
The author discusses a problem where scheduled AI workflows run successfully without completing the target task, and proposes a solution focusing on workflow targets with checkpointing and continuous progress until completion.
Running 11 research agents in parallel for a data sweep cut processing time in half but revealed failures like empty briefs and API rate limits, emphasizing that orchestration and verification are more critical than the specific tool used.
AIPOCH has released a curated library of over 550 medical research agent skills supporting evidence insights, protocol design, data analysis, and academic writing, compatible with multiple AI agent platforms like Claude Code and Codex.
The author critiques AI research tools for overconfidence in weak signals, praising Komo AI's rapid discovery and source-attached summaries but highlighting the need for better uncertainty and contradiction handling. They describe a workflow that splits discovery, verification, and structured checking across multiple AI tools.
A user shares three Hermes AI agent workflows for daily research and investment, including tracking analyst posts, synthesizing bookmarks, and onchain forensics to improve decision-making.
Sourclip is a tool that turns NotebookLM into a complete research workflow, enhancing its capabilities for research and note-taking.
Bibby AI is an editor-native platform that integrates the academic writing pipeline from literature discovery to submission, using agents that operate on document syntax representations to perform citation insertion, structural edits, and formatting.
The author advocates for LLM Wikis as a valuable application of AI, showcasing their PaperWiki project that uses agents to automatically curate and maintain a knowledge base of research papers, improving signal-to-noise ratio and enabling cutting-edge research.
A curated GitHub collection of AI skills for economists, organized by workflow stage to automate research tasks like data cleaning and econometrics, using open-source formats.
A Twitter thread detailing a structured workflow for AI-assisted research and writing, using NotebookLM for source ingestion, Claude for drafting, and Obsidian for knowledge management. Emphasizes the importance of solid source material and separating research from writing.
A paper co-authored by 37 authors from Stanford, CMU, Michigan, etc. proposes ARA (Agent-native Research Artifact) to replace the traditional paper format, aiming to solve the narrative tax and engineering tax, enabling AI agents to understand, reproduce, and extend research.
Academic Paper Skills is a paper writing skill framework for Claude Code, dividing the writing process into two phases: strategy and composition. It incorporates features like literature support, reviewer simulation, and quality checks to help users generate a first draft from a research idea.
A GitHub repository packages academic research skills into a single Codex skill, covering literature review, paper writing, peer review, and experiment planning to streamline the research workflow using OpenAI's Codex.
Recommends the open-source repository academic-research-skills, which provides a set of human-AI collaborative tools for the entire academic research workflow, including in-depth literature research, paper writing, peer review simulation, and citation audit. It supports AI assistance while keeping the user in control, suitable for graduate students and researchers.