Page 6 of 11
Listed inChain of ThoughtPrompt Engineeringon
On models that reason by default, asking for step-by-step thinking pays for the steps twice. Carried-over verification instructions cause over-verification, and tag conventions are a weak way to separate reasoning from the answer.
Listed inJina EmbeddingsEmbeddingson
A 32,768-token context means the encoder stops dictating your chunk size. Task types move the query-versus-passage distinction into a parameter a reviewer can see, and truncatable vectors have one way to cut them safely.
Listed inNano Banana APIMultimodal AIon
The nickname is the documented product name for Gemini's native image generation. Multi-turn conversation is the recommended way to change an image, reference budgets are capped by category and in total, and every result carries a SynthID watermark.
Listed inAI Engineer vs ML EngineerIntroductionon
One role starts with data and produces a model; the other starts with a model and produces a system. Both use the word evaluation for different things, which is where the two talk past each other.
Listed inMeta LlamaModels & Providerson
Downloadable weights come under a custom licence rather than Apache or MIT. It requires a "Built with Llama" notice, a model name beginning with Llama, and a separate agreement above 700 million monthly active users.
Listed inChromaVector Databaseson
The persistent client gets a working query with no infrastructure decision, and the collection code survives the move to a server. Concurrency, the directory's lifetime and backups are the bill that arrives with traffic.
Listed inBuilding an MCP ServerModel Context Protocolon
The input schema tells the model what to send as well as validating what arrives. Returning tools in a stable order protects callers' prompt caches, and an error that names the rule lets the model correct itself.
Listed inModel-Based EvalsEvaluationon
A judge answers what code cannot decide, and costs a model call per case while being able to be wrong. Validate it on ranking rather than absolute scores, and test it for grader hacking, position bias and verbosity bias.
Listed inTrainingIntroductionon
Pre-training, post-training, and RLHF — the parts you rarely do but always need to reason about.
Listed inOllamaModels & Providerson
One command pulls a packaged build and serves it, which means a quantization was chosen for you. Compatible client surfaces let existing code point at it, and a single-user local runner is no evidence about serving traffic.
Listed inMongoDB Atlas Vector SearchVector Databaseson
Vector indexes inside documents you already store.
Listed inContext SourcesContext Engineeringon
Docs, databases, tickets, telemetry, and the user's own session.
Listed inCost & Latency MonitoringObservabilityon
Output, cache reads, cache writes and batch requests are priced differently, so one token total cannot produce a bill. Record time to first token apart from total duration, and alert on ratios rather than on spend that grows with success.
Listed inTemperatureHow LLMs Workon
The randomness dial: what it does to the distribution, and sane defaults per task.
Listed inTransformers.jsModels & Providerson
Running transformer models in the browser with WebGPU and WASM.
Listed inRetrieval ProcessRAGon
Query rewriting, hybrid search, reranking, and how many chunks to actually pass.
Listed inMemory SystemsContext Engineeringon
Short-term, episodic, and semantic memory across sessions.
Listed inAI Safety and EthicsSafety & Ethicson
The obligations that come with shipping a system you cannot fully predict.
Listed inPrompt EngineeringPrompt Engineeringon
The discipline of specifying a task precisely enough that a model can't drift.