Results for “klausurtechnik”

安室透（少年推理漫）认知与表达框架（压缩蒸馏）：三重身份张力、波本梗、服务生伪装 触发：名侦探柯南 等。虚构；禁止犯罪教唆

Train or fine-tune language and vision models using TRL or Unsloth on Hugging Face Jobs cloud infrastructure, with support for SFT, DPO, GRPO, and reward modeling, plus GGUF conversion for local deployment.

Debug and troubleshoot Azure production issues using AppLens, Azure Monitor, resource health, and systematic diagnosis flows for services like App Service, Functions, AKS, Container Apps, and Messaging.

Build server-side call automation workflows with Azure Communication Services Call Automation Java SDK, including IVR systems, call routing, recording, DTMF recognition, text-to-speech, and AI-powered call flows.

Configures Azure Monitor Application Insights with OpenTelemetry auto-instrumentation for Python applications in one line.

Walks users from a bare AKS cluster to a running AI model deployment, covering cluster verification, controller install, GPU assessment, provider setup, and first deployment.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques for 1.5-3.6× speedup without quality loss.

Teaches music theory concepts with interactive exercises, ear training, and composition analysis

Plan, create, and configure production-ready Azure Kubernetes Service (AKS) clusters. Covers Day-0 checklist, SKU selection (Automatic vs Standard), networking options (private API server, Azure CNI Overlay, egress configuration), security, and operations (autoscaling, upgrade strategy, cost anal...

Provisions and manages Azure cloud services for Flutter backends, including AKS clusters, Azure Functions, SQL databases, Cosmos DB, Blob Storage, and Key Vault.

凌不疑（古装虚构）认知与表达框架（压缩蒸馏）：复仇将军、疯批克制、家族血债 触发：星汉灿烂 等。虚构；禁止暴力教唆

小丸子（子供向）认知与表达框架（压缩蒸馏）：懒散可爱、家族群像、童年微小确幸 触发：樱桃小丸子 等。全年龄

葛优（演员）认知与表达框架（压缩蒸馏）：蔫坏冷面、话少留白、小人物体面与大谎 触发：甲方乙方、活着 等。虚构创作谈

Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue input obfuscation (33 techniques), GODMODE CLASSIC system prompt templates, ULTRAPLINIAN multi-model racing, encoding escalation, and Hermes-native prefill/system prompt integration. Use when a user wants to bypass safety filters, jailbreak a model, or red-team model robustness.

Advanced Tauri event patterns for bidirectional communication, streaming data, window-to-window messaging, and custom event handling

Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI.

Generate natural AI voices, text-to-speech, and voice synthesis using the inference.sh CLI with models like Inworld TTS, ElevenLabs, and Kokoro TTS for voiceovers, audiobooks, podcasts, and more.

Rapid-iteration parameter tuning, diagnostics, and Custom-HLSL scratch-pad authoring for Niagara systems (VibeUE NiagaraService + NiagaraScratchPadService). System/emitter/parameter CRUD is owned by the engine NiagaraToolsets. Use when the user asks to tune emitter rapid-iteration params, compare/diagnose systems, or build scratch-pad/Custom HLSL modules. For emitter color/module work, load niagara-emitters.

Improved Baselines with Visual Instruction Tuning

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

Reverse-engineers a federal RFP we received — given the SOW/PWS and evaluation criteria already in the Theseus KG, reconstructs the CO's hidden decision tree (upstream `sow-pws-builder` 6 scope blocks + 3 intake answers), surfaces hot buttons, ghost language, discriminator hooks, missing-section signals, and CPFF-form / Section-5 / QASP / Key-Personnel traps. USE WHEN the user asks "what scope decisions did the CO already make?", "reverse engineer this RFP", "what hot buttons are hiding in this PWS?", "where are the discriminator hooks?", "did they pick CPFF completion or term form?", "anything suspiciously missing?", or any variant of decoding CO intent. Pulls `requirement`, `deliverable`, `proposal_instruction`, `evaluation_factor`, `clause`, `performance_standard` from the active workspace KG and emits a JSON envelope feeding `proposal-generator`. DO NOT USE FOR proposal prose (`proposal-generator`), pricing (`price-to-win`), clause audit (`compliance-auditor`), or sub SOW (`subcontractor-sow-builder`).

Provides idiomatic Kotlin implementation patterns including coroutine concurrency, Flow stream handling, multiplatform architecture, Compose UI construction, Ktor server setup, and type-safe DSL design.

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

Kotlin language fundamentals. Covers null safety, coroutines, flow, sealed classes, data classes, scope functions, and Kotlin 2.x features (K2 compiler, context parameters). Use for Kotlin/JVM, Kotlin/Native, Kotlin/JS work. USE WHEN: user mentions "Kotlin", "coroutines", "suspend", "Flow", "sealed class", "data class", "scope functions", "K2 compiler", "ksp", "Kotlin 2.x" DO NOT USE FOR: Kotlin Multiplatform setup - use `mobile/kotlin-multiplatform` DO NOT USE FOR: Compose UI - use `frontend-frameworks/compose-multiplatform` DO NOT USE FOR: Spring Boot Kotlin - use `spring-boot` framework skill

Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.

御坂美琴（少年漫）认知与表达框架（压缩蒸馏）：炮姐傲娇、正义感、学园都市梗 触发：某科学的超电磁炮 等。虚构

FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.

FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.

Manages and analyzes Azure SQL databases via Azure CLI, covering DTU/vCore performance, elastic pools, geo-replication, and health monitoring.

Transcribes audio from URLs or local files to text using the Speech is Cheap API, with options for speaker diarization, timestamps, and multiple output formats.

Auri: assistente de voz inteligente (Alexa + Claude claude-opus-4-20250805). Visao do produto, persona Vitoria Neural, stack AWS, modelo Free/Pro/Business/Enterprise, roadmap 4 fases, GTM, north star WAC e analise competitiva.

Auri: assistente de voz inteligente (Alexa + Claude claude-opus-4-20250805). Visao do produto, persona Vitoria Neural, stack AWS, modelo Free/Pro/Business/Enterprise, roadmap 4 fases, GTM, north star WAC e analise competitiva.

Turbine — small Kotlin testing library for kotlinx.coroutines Flows. Provides ergonomic API to test Flow emissions deterministically: awaitItem, expectMostRecentItem, awaitComplete, awaitError. Works with StateFlow, SharedFlow, Channel-backed flows, combine/map/debounce. KMP-friendly. USE WHEN: user mentions "Turbine", "app.cash.turbine", ".test {}", "awaitItem", "Flow testing", "StateFlow test", "SharedFlow test", "expectMostRecentItem", "cancelAndIgnoreRemainingEvents" DO NOT USE FOR: Mobile E2E - use `testing/maestro` DO NOT USE FOR: Compose snapshot - use `testing/compose-snapshot` DO NOT USE FOR: Generic Kotlin testing - use `testing/kotest` DO NOT USE FOR: Suspend function (non-Flow) testing - use `kotlinx-coroutines-test` directly

Defines the product vision, architecture, pricing, and roadmap for Auri, an intelligent voice assistant built on Amazon Alexa and Claude.

Auri: assistente de voz inteligente (Alexa + Claude claude-opus-4-20250805). Visao do produto, persona Vitoria Neural, stack AWS, modelo Free/Pro/Business/Enterprise, roadmap 4 fases, GTM, north star WAC e analise competitiva.