o caminho mínimo
os 81 verbetes marcados como núcleo, de 221: se só puder ler alguns, são estes. cada estante na ordem que ela promete, e a estante inteira está a um clique no título.
ia generativa19 de 61
- Efficient Estimation of Word Representations in Vector Space
- Attention Is All You Need
- Deep Reinforcement Learning from Human Preferences
- Improving Language Understanding by Generative Pre-Training
- Language Models are Unsupervised Multitask Learners
- Language Models are Few-Shot Learners
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Scaling Laws for Neural Language Models
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Constitutional AI: Harmlessness from AI Feedback
- ReAct: Synergizing Reasoning and Acting in Language Models
- Training Compute-Optimal Large Language Models
- Training language models to follow instructions with human feedback
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- Lost in the Middle: How Language Models Use Long Contexts
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- The Llama 3 Herd of Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
claude, na prática15 de 41
- Prompt engineering overview
- Define your success criteria
- Tool use with Claude
- Writing effective tools for AI agents
- Advanced tool use
- Prompt caching
- Introducing Contextual Retrieval
- Effective context engineering for AI agents
- Building effective agents
- Model Context Protocol
- How we built our multi-agent research system
- Effective harnesses for long-running agents
- Claude Code overview
- Claude Code: Best practices for agentic coding
- Demystifying evals for AI agents
dados e armazenamento10 de 32
- A Relational Model of Data for Large Shared Data Banks
- The Log-Structured Merge-Tree (LSM-Tree)
- Dynamo: Amazon's Highly Available Key-value Store
- Dremel: Interactive Analysis of Web-Scale Datasets
- Gorilla: A Fast, Scalable, In-Memory Time Series Database
- Amazon Aurora: Design Considerations for High Throughput Cloud-Native Relational Databases
- Amazon DynamoDB: A Scalable, Predictably Performant, and Fully Managed NoSQL Database Service
- What Goes Around Comes Around... And Around...
- C-Store: A Column-oriented DBMS
- The Snowflake Elastic Data Warehouse
sistemas distribuídos17 de 33
- Time, Clocks, and the Ordering of Events in a Distributed System
- Paxos Made Simple
- The Google File System
- MapReduce: Simplified Data Processing on Large Clusters
- Bigtable: A Distributed Storage System for Structured Data
- The Chubby lock service for loosely-coupled distributed systems
- Spanner: Google's Globally-Distributed Database
- Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing
- The Tail at Scale
- In Search of an Understandable Consensus Algorithm
- Large-scale cluster management at Google with Borg
- Zanzibar: Google's Consistent, Global Authorization System
- Millions of Tiny Databases
- Firecracker: Lightweight Virtualization for Serverless Applications
- Brewer's Conjecture and the Feasibility of Consistent, Available, Partition-Tolerant Web Services
- Dapper, a Large-Scale Distributed Systems Tracing Infrastructure
- Kafka: a Distributed Messaging System for Log Processing
estruturas e algoritmos6 de 17
- Probabilistic Counting Algorithms for Data Base Applications
- Consistent Hashing and Random Trees: Distributed Caching Protocols for Relieving Hot Spots on the World Wide Web
- HyperLogLog: the analysis of a near-optimal cardinality estimation algorithm
- Designing Access Methods: The RUM Conjecture
- SIEVE is Simpler than LRU: an Efficient Turn-Key Eviction Algorithm for Web Caches
- Skip Lists: A Probabilistic Alternative to Balanced Trees
busca e recuperação5 de 22
- The Anatomy of a Large-Scale Hypertextual Web Search Engine
- Detecting Near-Duplicates for Web Crawling
- The Probabilistic Relevance Framework: BM25 and Beyond
- Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs
- Dense Passage Retrieval for Open-Domain Question Answering