Whisper API
Listed inWhisper APIMultimodal AIon
OpenAI's transcription model, hosted and self-hosted.
Beginner5 minDraft
#api
Page 10 of 11
Listed inWhisper APIMultimodal AIon
OpenAI's transcription model, hosted and self-hosted.
Listed inRoles and ResponsibilitiesIntroductionon
The day-to-day surface area: prompts, retrieval, evals, latency budgets, and cost control.
Listed inMistralModels & Providerson
Small, fast, permissively licensed models and mixture-of-experts variants.
Listed inPineconeVector Databaseson
Fully managed, serverless vector search with namespaces and metadata filters.
Listed inBuilding an MCP ClientModel Context Protocolon
Connecting, listing capabilities, and wiring calls into your own loop.
Listed inHuman EvalsEvaluationon
Rubrics, annotator agreement, and when humans are the only ground truth.
Listed inHow LLMs WorkHow LLMs Workon
Next-token prediction, attention, and the path from raw text to a streamed response.
Listed inLM StudioModels & Providerson
A desktop GUI for pulling, comparing, and serving local models.
Listed inWhat is RAG?RAGon
Retrieval-augmented generation: fetch relevant context, then answer from it.
Listed inContext CompactionContext Engineeringon
Summarising and pruning history so long sessions stay affordable.
Listed inProduction MonitoringObservabilityon
Drift, failure rates, and alerting on quality instead of just uptime.
Listed inTop-PHow LLMs Workon
Nucleus sampling — trimming the tail by probability mass instead of by rank.
Listed inUsing SDKs DirectlyAPIs & SDKson
Skipping the framework and calling the provider client — usually the right first move.
Listed inGenerationRAGon
Composing retrieved context into a prompt that forces grounded answers.
Listed inExternal MemoryContext Engineeringon
Offloading state to files, databases, and scratchpads outside the window.
Listed inPrompt Injection AttacksSafety & Ethicson
Untrusted text that rewrites your instructions, and why filtering isn't enough.
Listed inInput FormatPrompt Engineeringon
Structuring what you send — delimiters, sections, and formats models parse reliably.
Listed inSemantic SearchEmbeddingson
Retrieving by meaning instead of keywords, and where it still loses to BM25.
Listed inAgent Use CasesAI Agentson
Where a loop beats a pipeline, and where it just adds variance.
Listed inImage UnderstandingMultimodal AIon
Passing images to a model and getting reliable structured answers back.