Google 《Prompt Engineering v7》Prompt Engineering Author: Lee Boonstra Prompt Engineering February 2025 2 Acknowledgements Content contributors Michael Sherman Yuan Cao Erick Armbrust Anant Nawalgaria Antonio Gulli Simone Cammel Grace Mollison Technical Writer Joey Haymaker Designer Michael Lanning Introduction 6 Prompt engineering 7 LLM output configuration 8 Output length 8 Sampling controls 9 Temperature 9 Top-K and (CoT) 29 Self-consistency 32 Tree of Thoughts (ToT) 36 ReAct (reason & act) 37 Automatic Prompt Engineering 40 Code prompting 42 Prompts for writing code 42 Prompts for explaining code 44 Prompts0 码力 | 68 页 | 6.50 MB | 6 月前3
Performance Engineering: Being Friendly to Your HardwareBeing Friendly to Your Hardware Performance Engineering A gentle introduction to hardware for software engineers 2Where does C++ run? 3On an abstract C++ machine 4On an abstract C++ machine?0 码力 | 111 页 | 2.23 MB | 6 月前3
No Silver Bullet – Essence and Accident in Software EngineeringNo Silver Bullet – Essence and Accident in Software Engineering Mike Ballou“There is no single development, in either technology or management technique, which by itself promises even one order-of- published The Mythical Man-Month: Essays on Software Engineering • In 1987, authored No Silver Bullet – Essence and Accident in Software Engineering“We hear desperate cries for a silver bullet – something0 码力 | 35 页 | 1.43 MB | 5 月前3
SQLite Tutorialsqlite3.exe files. Add C:\>sqlite in your PATH environment variable and finally go to the command prompt and issue sqlite3 command, which should display a result something as below. C:\>sqlite3 SQLite instructions Enter SQL statements terminated with a ";" sqlite> Finally, you have SQLite command prompt where you can issue SQLite commands to do your excercises. TUTORIALS POINT Simply Easy semi-colon (;). Let's start with typing a simple sqlite3 command at command prompt which will provide you SQLite command prompt where you will issue various SQLite commands. $sqlite3 SQLite version 30 码力 | 172 页 | 1.27 MB | 1 年前3
DeepSeek-V2: A Strong, Economical, and Efficient
Mixture-of-Experts Language Modelserve a much larger batch size. We evaluate the generation throughput of DeepSeek-V2 based on the prompt and generation length distribution from the actually deployed DeepSeek 67B service. On a single node per second, which is 5.76 times the maximum generation throughput of DeepSeek 67B. In addition, the prompt input throughput of DeepSeek-V2 exceeds 100K tokens per second. 4. Alignment 4.1. Supervised Fine-Tuning an instruction-following evaluation (IFEval) (Zhou et al., 2023) for DeepSeek-V2 Chat (SFT), using prompt-level loose accuracy as the metric. Moreover, we employ LiveCodeBench (Jain et al., 2024) questions0 码力 | 52 页 | 1.23 MB | 1 年前3
OpenAI 《A practical guide to building agents》new category of LLM-powered systems known as agents. This guide is designed for product and engineering teams exploring how to build their first agents, distilling insights from numerous customer deployments customer service for example, routines can roughly map to individual articles in your knowledge base. Prompt agents to break down tasks Providing smaller, clearer steps from dense resources helps minimize like o1 or o3-mini, to automatically generate instructions from existing documents. Here’s a sample prompt illustrating this approach: Unset 1 “You are an expert in writing instructions for an LLM agent.0 码力 | 34 页 | 7.00 MB | 6 月前3
Trends Artificial Intelligence
Stanford University… 1: AI ‘Winter’ was a term used by Nils J. Nilsson, the Kumagai Professor of Engineering in computer science at Stanford University, to describe the period during which AI continued to would understand goals, generate plans, and self-correct in real time. They could drive research, engineering, education, and logistics workflows with little to no human oversight – handling ambiguity and databases. Model development = frameworks for modeling & training, inference optimization, dataset engineering, & model evaluation. Application development = custom AI-powered applications (varied use cases)0 码力 | 340 页 | 12.14 MB | 4 月前3
Linux Lab v1.3 Manualfor C programmer, with examples verified in Linux Lab • 《Software Reverse Engineering Quickstart》 – Learn reverse engineering by practice, with examples verified in Linux Lab • 《Linux Kernel Livepatch gdb/kernel. default, run gdb automatically. But if login with bash, ssh or webssh, please read the prompt and run this command again to start debugging: 1 $ make debug To customize kernel gdbinit script terminal and start debugging automatically. But if login with bash, ssh or webssh, please read the prompt and run this command again to start real debugging: 1 $ make debug uboot To automate U-Boot debug0 码力 | 66 页 | 1.12 MB | 1 年前3
Linux Lab v1.2 Manualfor C programmer, with examples verified in Linux Lab • 《Software Reverse Engineering Quickstart》 – Learn reverse engineering by practice, with examples verified in Linux Lab • 《Linux Kernel Livepatch gdb/kernel. default, run gdb automatically. But if login with bash, ssh or webssh, please read the prompt and run this command again to start debugging: 1 $ make debug To customize kernel gdbinit script terminal and start debugging automatically. But if login with bash, ssh or webssh, please read the prompt and run this command again to start real debugging: 1 $ make debug uboot To automate U-Boot debug0 码力 | 67 页 | 1.13 MB | 1 年前3
Linux Lab v1.1 Manualfor C programmer, with examples verified in Linux Lab • 《Software Reverse Engineering Quickstart》 – Learn reverse engineering by practice, with examples verified in Linux Lab • 《Linux Kernel Livepatch gdb/kernel. default, run gdb automatically. But if login with bash, ssh or webssh, please read the prompt and run this command again to start debugging: 1 $ make debug To customize kernel gdbinit script terminal and start debugging automatically. But if login with bash, ssh or webssh, please read the prompt and run this command again to start real debugging: 1 $ make debug uboot To automate U-Boot debug0 码力 | 65 页 | 1.12 MB | 1 年前3
共 1000 条
- 1
- 2
- 3
- 4
- 5
- 6
- 100













