604 个 · 按相关度排序
Use Phoenix to record execution traces, detailed records of an AI application's operations, and investigate problems. Evaluate answers on datasets, compare prompts and models, and set up monitoring through a self-hosted server.
中文简介正在准备中。当前显示英语简介。
Learn how GPT language models work by preparing text, training a small model, and generating samples. Covers CPU experiments, custom datasets, further training of pretrained GPT-2 models, and reproducing GPT-2 with multiple GPUs.
中文简介正在准备中。当前显示英语简介。
Organize research papers and notes in Drive, write summaries in Docs, and log data in Sheets. Share findings with collaborators and send peer review requests through Gmail to support research teamwork.
中文简介正在准备中。当前显示英语简介。
Review product performance by comparing usage, retention, revenue, and other metrics with previous periods and targets. Turn the numbers into a scorecard, explain meaningful trends and uncertainties, and recommend investigations or improvement experiments.
中文简介正在准备中。当前显示英语简介。
Explore product problems, generate alternative solutions, and challenge the assumptions behind an idea through conversation. It helps product managers compare directions, identify weak points, and choose questions or experiments to investigate before committing to development.
中文简介正在准备中。当前显示英语简介。
Analyze single-cell data with scvi-tools, using deep learning to combine datasets, correct differences between experiments, and transfer cell labels. Model guides and reusable scripts cover RNA, protein, chromatin accessibility, spatial data, and downstream analysis.
中文简介正在准备中。当前显示英语简介。
Run smoke tests, or basic operational checks, for Mastra projects locally or in staging and production. Verify Studio screens, agents, tools, workflows, traces, and memory, then report results, blockers, and skipped checks.
中文简介正在准备中。当前显示英语简介。
Route enterprise research questions to specialized skills for clinical studies, R&D finance, market research, or user research. Receive a concise digest of findings, next actions, output files, and assumptions that need human review.
中文简介正在准备中。当前显示英语简介。
Evaluate product ideas before committing development resources. Organize customer needs, rank uncertain assumptions, and plan interviews or prototype tests in a short discovery cycle that ends with evidence for proceeding, changing direction, or stopping.
中文简介正在准备中。当前显示英语简介。
Design and improve in-app screens that invite users to paid plans. Develop complete screen copy, prompt timing rules, upgrade flows, and experiment ideas based on the value users have already experienced.
中文简介正在准备中。当前显示英语简介。
Plan A/B tests that compare page variations, from headlines to pricing layouts. Define a hypothesis, choose success metrics, calculate sample size and duration, and prepare launch checks and results reports to support decisions.
中文简介正在准备中。当前显示英语简介。
Turn a new product idea into a canvas covering nine strategy areas plus costs and revenue. Clarify target customers, value, priorities, and growth, then identify assumptions and simple experiments to test them.
中文简介正在准备中。当前显示英语简介。
Turn a product idea into a Lean Canvas, a nine-part outline of business assumptions. Define customer problems, solutions, value, channels, revenue, costs, and metrics, then identify risky assumptions and suggest experiments to test them.
中文简介正在准备中。当前显示英语简介。
Guides machine learning work from data preparation and model training to evaluation and production monitoring. Covers PyTorch, scikit-learn, experiment tracking, and reproducible workflows so teams can compare models and maintain them after deployment.
中文简介正在准备中。当前显示英语简介。
Check experimental results before making research claims. A fresh reviewer examines reference data, score calculations, result files, and evaluation scope, then produces an evidence-based report showing which claims are supported and which need qualification.
中文简介正在准备中。当前显示英语简介。
Rent and manage vast.ai GPUs based on the training task rather than a chosen hardware model. The skill estimates requirements, compares offers by total expected cost, prepares the selected instance, and retrieves results before destroying it.
中文简介正在准备中。当前显示英语简介。
Turn a vague research direction into a focused proposal and a detailed experiment roadmap. This workflow connects method refinement with validation planning, producing review records, an experiment tracker, and a summary of what to run next.
中文简介正在准备中。当前显示英语简介。
Understand a single arXiv paper through an AlphaXiv summary, with full text and LaTeX source available when needed. Use it to identify key findings or ask specific questions about methods, experiments, and equations.
中文简介正在准备中。当前显示英语简介。
Turn a research proposal into an experiment plan tied to specific paper claims. Define comparisons, evaluation measures, tests that remove individual components, run order, and compute estimates, with a written plan and tracker for execution.
中文简介正在准备中。当前显示英语简介。
Compare machine learning experiment results from JSON or CSV files. Calculate improvements over a baseline, summarize variation across repeated runs, identify trends and unusual results, and suggest experiments to test possible explanations.
中文简介正在准备中。当前显示英语简介。
Triage incorrect MNN outputs and regressions by matching symptoms to focused debugging guides. Use backend comparisons, minimal reproductions, and controlled experiments to investigate memory issues, quantization, concurrency, numeric limits, caches, and inconsistent results across runs.
中文简介正在准备中。当前显示英语简介。
Plan systems conference papers with section page budgets, paragraph outlines, and writing patterns. Organize design choices, experimental evidence, and related work into a clear argument, then review the draft with submission checklists.
中文简介正在准备中。当前显示英语简介。
Use Phoenix to record execution traces, detailed records of an AI application's operations, and investigate problems. Evaluate answers on datasets, compare prompts and models, and set up monitoring through a self-hosted server.
中文简介正在准备中。当前显示英语简介。
Explore research directions through ten structured thinking frameworks, then rank ideas by their importance, clarity, and feasibility. Turn a vague interest into a focused proposal with a short explanation, candidate experiments, and an initial feasibility study.
中文简介正在准备中。当前显示英语简介。