Skip to content
tezvyn:

LLM

157 bites tagged LLM — interview questions with model answers, and 60-second explainers.

LLMs & Generative AI1 min read

When to choose RAG over fine-tuning

RAG for fresh, factual, citable knowledge that changes often, fine-tuning for behavior, style, or format the model must internalize. matching technique to the kind of adaptation needed.

LLMs & Generative AI1 min read

Differential privacy vs utility in LLM fine-tuning

Clipping plus calibrated noise per step, smaller epsilon means stronger privacy but degraded accuracy, tracking the privacy budget across epochs. understanding DP-SGD's noise-for-privacy bargain.

LLMs & Generative AI1 min read

Rule-based versus model-based LLM guardrails

A guardrail is a programmatic check constraining LLM I/O; rule-based uses regex or blocklists, model-based uses a classifier like a moderation model to detect harmful content. practical safety controls.

LLMs & Generative AI1 min read

Teacher-student knowledge distillation

A small student learns to mimic a large teacher's soft probability outputs, not just hard labels; goal is a compact model retaining most capability. grasp of model compression via distillation.

LLMs & Generative AI2 min read

How the KV cache speeds transformer generation

Cache stores past keys and values so each new token only computes its own K, Q, V instead of recomputing all prior tokens, cutting per-step cost from quadratic to linear. understanding attention during decoding.

LLMs & Generative AI1 min read

Model quantization benefits and risks

Quantization stores weights and activations in lower precision like INT8 or INT4; benefits are smaller memory and faster, cheaper inference; risk is accuracy loss. deployment-efficiency fundamentals.

LLMs & Generative AI1 min read

Prompt injection versus jailbreak, and defenses

Injection hijacks the model via untrusted data overriding developer instructions; jailbreak coaxes a model past its safety policy. Defense: separate trusted instructions from untrusted data and filter. precise security distinctions.

LLMs & Generative AI1 min read

Red teaming LLMs and harmful output categories

Red teaming deliberately probes a model to elicit harmful behavior; categories include toxic or hateful content and dangerous instructions like weapons or malware. understanding adversarial safety testing.

LLMs & Generative AI1 min read

Setting up an LLM-as-a-judge evaluation

Define rubric, prefer pairwise comparison, randomize order, calibrate against humans; control position, verbosity, and self-preference bias. rigorous LLM-as-judge design.

LLMs & Generative AI1 min read

How MMLU works and the contamination problem

MMLU is multiple-choice across 57 subjects scored by accuracy; contamination means test items leaked into pretraining, inflating scores. understanding of LLM benchmarks and their flaws.

LLMs & Generative AI1 min read

How to evaluate a RAG system end to end

Measure retrieval (recall, precision, MRR, NDCG) and generation (faithfulness, answer relevance) separately, plus end-to-end correctness. ability to decompose RAG evaluation. judging only final answer quality with one number.

LLMs & Generative AI2 min read

Zero-Shot, Few-Shot, and Chain-of-Thought Trade-offs

Zero-shot is cheap but weak on reasoning, few-shot adds demos at token cost, CoT boosts multi-step accuracy but spends the most tokens and latency. judgment about prompting strategies.

LLMs & Generative AI1 min read

Hallucination Detection in LLMs

Hallucination detection is the set of techniques for flagging when a language model states something fluent but false or unsupported, using signals like self-consistency, model uncertainty, and grounding against retrieved evidence to catch fabrications before…

CI/CD & Automation1 min read

GitHub Copilot tunes context windows and routing

GitHub Copilot is improving how it handles context windows and routes requests between models. Better token efficiency and smarter routing mean faster, more relevant code suggestions for developers using the tool daily.

MLOps & Infrastructure1 min read

Most LLM Apps Need Workflows Not Agent Frameworks

Most LLM apps ship faster and more reliably as deterministic workflows than autonomous agents. Plain Python with structured outputs and local functions beats CrewAI and LangGraph for debugging. Map control flow in code before importing any agent framework.

LLMs & Generative AI2 min read

How would you architect a multi-turn conversational RAG system?

This tests memory and query reformulation design beyond single-turn RAG. A strong answer covers 5-10 turn windows, LLM-based rewriting with coreference resolution, hybrid fallbacks, and summarized memory.

LLMs & Generative AI2 min read

Identify RAG latency bottlenecks and propose optimizations

This tests systems thinking across the RAG pipeline. A strong answer names four bottlenecks—embedding, search, chunking, and generation—and pairs each with caching, index tuning, and distillation. Red flag: GPU scaling without indexing fixes.

LLMs & Generative AI2 min read

Why does your RAG ignore or contradict retrieved context?

Tests separation of retrieval failures from generation grounding in RAG. Strong answers trace symptoms to root causes like bad chunks, prompt ordering, or parametric knowledge override, then outline systematic debugging. Do not just say hallucination.

LLMs & Generative AI2 min read

NIST AI RMF for LLM Deployment

The NIST AI RMF is a pre-flight checklist for organizational AI risk, not just code bugs. Teams use it to justify LLM deployment across legal, security, and fairness dimensions.

LLMs & Generative AI2 min read

Tool Definition Schema: Contracts for LLM Actions

A tool schema is JSON that tells an LLM what actions it can take. Use it when you want the model to call APIs instead of just chatting. The model only emits arguments; it never runs the tool, and vague descriptions cause silent failures.

Content & Copywriting2 min read

Design an LLM ad copy system with human-in-the-loop

LoRA on approved copy, inference guardrails, human review, feedback as preference pairs for RLHF. Architecture for fine-tuning, guardrails, and human feedback loops. Treating review as static gate, not training signal.

MLOps & Infrastructure2 min read

LLM Inference Caching: Pay for Computation Once

LLM inference caching reuses past computations to cut costs and latency. It avoids reprocessing shared system prompts or serves full answers for common queries without hitting the model. The footgun: semantic caches can return a "similar" but incorrect answer.

MLOps & Infrastructure2 min read

Microsoft DeepSpeed: Training Massive Models Across GPUs

DeepSpeed trains models too big for one GPU by partitioning model states across many devices. It's essential for training foundation models like BLOOM, but its complexity is overkill for smaller models and misconfiguration can harm performance.

LLMs & Generative AI2 min read

Open LLM Leaderboard: Separating Hype from Performance

The Open LLM Leaderboard is the de facto scoreboard for open-source models, providing reproducible benchmarks to cut through marketing hype. It helps you compare models on standardized tests, but remember that a high rank doesn't guarantee performance on your…

Get LLM bites daily.

Five a day, five minutes, offline. With quizzes so it sticks.

Open testing — you’ll join as an early tester.