AI Foundations #39: Release Gates for AI Agents
Move beyond agent test scores: learn how release gates, staged autonomy, approvals, canary trials, monitoring, and rollback decisions work together.
Student Research Contributor — Mathematics & AI
machaMochaLatte
machaMochaLatte is a student research contributor focused on mathematics, artificial intelligence, scientific reasoning, and structured problem solving. Her writing examines technical ideas from the perspective of a student building deeper mathematical and engineering intuition, with particular interest in how foundational concepts connect to modern AI systems.
Published work
Articles
19 published
Disaggregated Prefill and Decode: Two Jobs Inside One LLM Request
AI Foundations #33 explains why LLM servers may separate prompt processing from token generation, how KV state moves, and the trade-offs between latency, throughput and operational cost.
By machaMochaLatte ·
Speculative Decoding: Why a Draft Model Can Speed Up a Larger LLM
AI Foundations #31 explains draft-and-verify generation, acceptance and rejection, why the target distribution can be preserved, and when speculative decoding actually reduces latency.
By machaMochaLatte ·
PagedAttention: How LLM Servers Stop KV Cache From Wasting Memory
AI Foundations #30 explains why variable-length KV caches fragment GPU memory, how paging divides cache into blocks, how logical token positions map to physical memory, and why this helps serving throughput.
By machaMochaLatte ·
Continuous Batching and Scheduling: How LLM Servers Share a GPU
AI Foundations #28 explains static batching, continuous batching, request scheduling, chunked prefill, head-of-line blocking, fairness, and why server throughput and user latency can pull in opposite directions.
By machaMochaLatte ·
Monitoring and Drift: How to Know an AI System Is Still Working
AI Foundations #26 explains production monitoring, data and concept drift, feedback loops, human review, and why a model that passed evaluation can still fail after deployment.
By machaMochaLatte ·
Tool Use and Agents: How AI Models Choose and Execute Actions
AI Foundations #24 explains tool use, function calling, agents, action loops, observations, permissions, failure modes, and why an LLM does not execute a tool by itself.
By machaMochaLatte ·
Evaluation and Benchmarks: How Do We Know an AI Model Is Better?
AI Foundations #22 explains test sets, metrics, benchmark design, sampling variance, contamination, and why a fair model comparison must control more than one score.
By machaMochaLatte ·
Multimodal AI: How Text, Images, and Audio Enter One Model
AI Foundations #20 builds a practical mental model of multimodal AI: how text, image, audio, and video representations are converted, aligned, and fed into transformer-style systems.
By machaMochaLatte ·
Quantization: How Fewer Bits Make Large Models Smaller
AI Foundations #18 explains post-training weight quantization, scale and rounding error, memory estimates, mixed precision, kernels, and quality tradeoffs.
By machaMochaLatte ·
Sampling: How Temperature, Top-k, and Top-p Choose the Next Token
AI Foundations #16 uses one probability distribution to show how greedy decoding, temperature, top-k, and top-p select the next token.
By machaMochaLatte ·
Fine-Tuning: How a Pretrained Model Learns a New Job Without Starting Over
AI Foundations #14 explains how fine-tuning continues gradient-based training from pretrained weights, using narrower data to change model behavior without relearning language from scratch.
By machaMochaLatte ·
Transformer: How Attention Becomes a Complete Neural Network Block
AI Foundations #12 assembles attention, residual connections, normalization, and MLP layers into the repeating Transformer block behind modern language models.
By machaMochaLatte ·
Tokenization: How Text Becomes the IDs an AI Model Can Read
AI Foundations #10 connects embeddings to tokenization: how text is split into tokens, mapped to vocabulary IDs, and then looked up as learned vectors.
By machaMochaLatte ·
Backpropagation: How a Neural Network Gets a Gradient for Every Weight
AI Foundations #8 explains backpropagation as repeated chain-rule bookkeeping that carries loss information backward through a neural network to every trainable parameter.
By machaMochaLatte ·
How Does a Neural Network Start Learning? Training Begins With Loss
AI Foundations #6 compares predictions with targets, calculates squared and absolute loss, aggregates a batch, and explains what loss can and cannot measure.
By machaMochaLatte ·
What Is a Tensor? The Shape of Data Inside AI
AI Foundations #4 explains tensor rank, shape, dtype, device, stride, element count, and memory through image and language-model examples.
By machaMochaLatte ·
What Does It Mean for a Machine to Learn?
AI Foundations #2 follows one parameter update to show how training data, a model, a loss function, gradients, and an optimizer create machine learning.
By machaMochaLatte ·
How I Use ChatGPT to Understand Math, Not Do My Homework
A student explains how to use ChatGPT for hints, error analysis, proofs, calculus, vectors, and practice while keeping the mathematical thinking.
By machaMochaLatte ·