'compute' 검색 결과

입자, 프랙털, 데이터의 움직임을 단일 HTML로 시각화합니다. 무거운 계산은 Web Worker로 분리하고 초당 약 60프레임을 목표로 화면을 그립니다.

• 입자와 물리 시뮬레이션 시제품 제작
• 프랙털 시각화
• 오디오와 데이터 시각화 화면 제작

Design agents that operate desktop or browser software through screenshots, mouse actions, and keyboard input. Compare ways to locate interface elements, diagnose coordinate errors, handle changing screens, and evaluate task completion, operating speed, and safety boundaries.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing screen-based automation for software without APIs
• Comparing methods for locating interface elements
• Investigating misclicks and coordinate scaling errors

Investigate how DNA variants may affect gene activity using precomputed AlphaGenome Atlas results and model predictions. Rank candidate variants, examine tissue-specific effects, and inspect the features behind scores to develop research hypotheses about biological mechanisms.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Ranking candidate variants from a VCF
• Examining tissue-specific effects on gene activity
• Comparing reference and altered DNA predictions

Organize Power Automate flows by business impact and responsible team using FlowStudio’s cached records. Find resources without active owners, audit connections to other services, review compliance metadata, and configure notifications for failures or missing runs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review flows for missing governance information
• Find resources owned by departing employees
• Audit connectors and premium license needs

Calculate how to divide serving memory between recurrent state and KV cache, two memory pools used by hybrid models. Use startup logs and workload settings to recommend a ratio, estimate concurrency, and identify the limiting pool.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a memory ratio for a hybrid model
• Investigating limits on concurrent requests
• Recalculating memory allocation for context length

Perform live Windows or macOS desktop tasks that dedicated tools cannot complete. The skill guides app and window selection, clicks, text entry, and keyboard actions, checking fresh screen information and verifying the requested result.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Completing desktop tasks without a suitable dedicated tool
• Entering and committing text in an app
• Selecting the correct window among similar windows

Analyze Zeek network logs to find lateral movement, when an intruder spreads between internal computers. Examine administrative file sharing, authentication across multiple hosts, and remote service operations to identify suspicious connections and reconstruct incident timelines.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Tracing spread to other computers after an initial compromise
• Investigating unauthorized transfers to administrative shares
• Finding one account authenticating to many internal hosts

Reconstruct activity on a compromised computer by combining file timestamps, event logs, browser history, and other evidence into one timeline. Extract and filter events with Plaso, then review and annotate them collaboratively in Timesketch.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reconstructing the sequence of a computer compromise
• Comparing events across logs and file records
• Investigating timestamp changes and cleared logs

Collect evidence from a compromised computer before shutdown or remediation erases it. Preserve memory, network connections, processes, and system state, then record integrity hashes and handling history to support incident investigation and evidence tracking.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preserving evidence before shutting down a compromised computer
• Collecting memory evidence for suspected fileless malware
• Recording active connections and processes during an intrusion

Analyze Windows event logs in Splunk to investigate suspicious logins, privilege changes, persistence, and movement between computers. Build detection searches and organize endpoint activity into timelines, with findings linked to MITRE ATT&CK attack techniques.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating suspicious Windows logins
• Building detection searches in Splunk
• Creating incident timelines

Build visual AI systems that detect objects or divide images into labeled regions. This skill guides dataset preparation, model selection, training, evaluation, inference optimization, and deployment using frameworks such as PyTorch and Ultralytics.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build an object detection pipeline
• Clean images and convert annotation formats
• Optimize a trained model for deployment

Let an agent launched through cmux inspect and operate macOS apps using screenshots and accessible interface elements. It supports clicking, typing, scrolling, and dragging, with explicit user requests and permissions granted to the local helper.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Ask an agent to click controls in a macOS app
• Enter text into forms or editors
• Check the screen after an action

Diagnose GKE TPU node pool creation or expansion failures despite reserved capacity. Trace which virtual machines and unhealthy node pools occupy reservation slots, check automatic repair settings, and provide remediation steps for the user to apply.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate TPU capacity errors despite a reservation
• Identify node pools occupying reserved TPU capacity
• Check automatic repair settings on unhealthy TPU nodes

Diagnose GKE TPU slice creation failures and pending JobSets caused by unstable managed instance groups, the underlying VM groups. Read-only checks examine logs, instance status, upgrades, and repairs to identify causes and suggest user-applied fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating TPU SliceCreationFailed errors
• Checking whether pending JobSets relate to MIG instability
• Tracing stalled node pool upgrades or repairs

Reviews Google Cloud spending and resource usage to identify waste, recommend suitable resource sizes, compare discount options, and establish ongoing cost management using the cost optimization guidance in the Google Cloud Well-Architected Framework.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing Google Cloud spending by team or project
• Finding idle resources and oversized instances
• Comparing CUDs, SUDs, and Spot VMs

Diagnose Google Cloud Filestore mount failures by checking client access rules, network firewalls, and audit logs. Distinguish permission errors from connection timeouts, then provide a structured report and remediation commands that require confirmation before execution.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a Filestore mount that hangs or fails
• Diagnosing access-denied errors from a GKE workload
• Checking client permissions and VPC firewall rules

Investigate interruptions affecting GPU and TPU workloads on GKE using maintenance labels, monitoring queries, logs, and node scheduling restrictions. The skill helps determine whether host maintenance caused a disruption and recommends workload protection measures when maintenance is confirmed or expected.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating unexpected GPU or TPU workload interruptions
• Checking upcoming host maintenance on GKE nodes
• Tracking maintenance interruptions with PromQL

Generate Terraform alerts for Cloud Run services, jobs, and worker pools using PromQL, a monitoring query language. Monitor errors, latency, resource usage, job failures, and queue delays, with configurable thresholds and explanations of when each alert triggers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Monitor Cloud Run service errors and latency
• Detect failed batch job executions
• Monitor worker pool backlogs and message age

Operate Chrome or Brave using signed-in browser sessions to verify deployed pages, reproduce bugs, inspect page structure, and examine errors or network traffic. An optional macOS bridge extends control to native applications and operating system input.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Verify page appearance after deployment
• Reproduce blank pages and disappearing content
• Inspect console errors and network traffic

Guide shell, Python, and Node.js execution on the computer running a connected A0 CLI. It explains session reuse, interactive input, output retrieval, and recovery steps when execution permissions, timeouts, or disconnections interrupt the work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run shell commands on the connected A0 CLI host
• Execute Python or Node.js on the host
• Retrieve output or answer an interactive program

Develop and migrate LangBot messaging adapters for Event-Based Agents, its event-driven architecture. Check conversion into shared event and message formats, implement platform APIs, and verify behavior through unit tests and real platform interactions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a messaging platform adapter to LangBot
• Migrating an existing adapter to the EBA layout
• Testing event and message conversion in both directions

Manage GPU compute jobs on Qizhi through a command-line tool. Find available nodes, submit distributed training runs, launch batches with different parameter combinations, and inspect, monitor, or stop jobs across workspaces.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding available GPU nodes across workspaces
• Submitting distributed training jobs
• Launching evaluation batches with different parameter combinations

Explore computer architecture and circuit design settings by repeatedly running programs, measuring results, and adjusting parameters. Compare configurations against a baseline, respect design constraints, and receive a report with the best configuration found and the search history.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Tune cache sizes and processor settings
• Reduce circuit area while meeting timing constraints
• Compare compiler flags for runtime or code size

Plan and run ablation studies, experiments that remove or replace parts of a method to test their contribution. Organize reviewer questions, priorities, expected outcomes, and compute costs, then record results and findings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Test how much each component contributes
• Plan experiments that address reviewer questions
• Prioritize comparisons within a compute budget