# Daily Dose of Data Science A free newsletter for continuous learning about data science and ML, lesser-known techniques, and how to apply them in 2 minutes. We keep things no-fluff. Join 100,000+ data scientists from top companies like Google, NVIDIA, Microsoft, Uber, etc. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## How to Fine-Tune LLMs in 2026 DevFeed: [How to Fine-Tune LLMs in 2026]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-16T20:40:26Z Content type: tutorial Language: en Sources: [Daily Dose of Data Science]() Topics: [Fine-tuning](), [Large Language Model](), [grpo](), [Artificial Intelligence]() Tags: [agents](), [ai](), [fine-tuning](), [llms](), [rl]() ### AI overview A developer newsletter explains how supervised fine-tuning differs from reinforcement fine-tuning for LLMs and describes GRPO and RULER as approaches for training agents through experience without manually written reward functions or labeled examples. It also briefly discusses Rowboat Spaces, an open-source shared workspace for personal AI assistants. ### Source excerpt Reward-free RL is here! ## Running Agent Harnesses with Local Models DevFeed: [Running Agent Harnesses with Local Models]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-15T21:59:31Z Content type: tutorial Language: en Sources: [Daily Dose of Data Science]() Topics: [Large Language Model](), [coding](), [Hardware](), [Open Source](), [Claude Code](), [codex]() Tags: [agent](), [coding](), [hardware](), [local](), [models](), [open-source](), [opentelemetry](), [profiling](), [recommendations](), [run-agent](), [video]() ### AI overview A video walkthrough explains how Magnitude profiles computer hardware, benchmarks local models, recommends practical candidates, and connects a selected model to coding agent harnesses such as Claude Code, Codex, OpenCode, and Pi. The article also presents a Dynatrace reference application for tracing LLM pipelines with OpenTelemetry. ### Source excerpt ...explained with a full video walkthrough. ## What It Takes to Build a Production Agent Harness DevFeed: [What It Takes to Build a Production Agent Harness]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-14T19:50:37Z Content type: article Language: en Sources: [Daily Dose of Data Science]() Topics: [Agent Harness](), [LangChain](), [Artificial Intelligence](), [Persistence](), [Graphs]() Tags: [agent](), [ai](), [ai-engineer](), [engineering](), [evaluation](), [langchain](), [langgraph](), [memory](), [persistence](), [tools](), [tracing]() ### AI overview A hands-on series chapter explains how to build a production agent harness with LangChain and LangGraph. It covers model, message, prompt, and tool interactions; tool-call execution; state transitions; persistence; failure handling; tracing; evaluation; human approval; and resumable execution. ### Source excerpt A hands-on nanodegree for production agent engineering. ## 4 Speculative Decoding Variants DevFeed: [4 Speculative Decoding Variants]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-12T20:03:46Z Content type: article Language: en Sources: [Daily Dose of Data Science]() Topics: [dynatrace](), [MCP](), [MCP Server](), [Traces](), [Latency]() Tags: [coding-agents](), [dynatrace](), [latency](), [mcp](), [mcp-server](), [traces]() ### AI overview This article explains how Dynatrace's open-source MCP server and related skills bring production traces and logs into coding agents for performance investigations. It also introduces speculative decoding, in which a cheaper drafter proposes tokens and a target model verifies them in parallel, then outlines variants based on how drafts are produced. ### Source excerpt ...covered with tradeoffs in production. ## The Architecture for Serving 100 Fine-Tuned Models on One GPU DevFeed: [The Architecture for Serving 100 Fine-Tuned Models on One GPU]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-11T21:25:15Z Content type: tutorial Language: en Sources: [Daily Dose of Data Science]() Topics: [GPU](), [vllm](), [Fine-tuning](), [lora](), [Serverless](), [Deployment](), [Code]() Tags: [code](), [deployment](), [fine-tuning](), [gpu](), [lora](), [memory](), [models](), [production](), [serverless](), [vllm](), [workers]() ### AI overview This tutorial compares architectures for serving 100 fine-tuned 7B model variants on GPUs. It explains how separate merged models increase storage, GPU memory use, scaling pools, cold starts, and idle capacity, while a shared base model with LoRA adapters enables adapter reuse through vLLM. The article plans to test merged, unmerged startup-loaded, request-time adapter loading, and hosted-per-tenant deployments on Runpod Serverless. ### Source excerpt ...explained with code. ## Caching Responses for Repeated Questions in Production LLM Applications DevFeed: [Caching Responses for Repeated Questions in Production LLM Applications]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-10T21:34:26Z Content type: article Language: en Sources: [Daily Dose of Data Science]() Topics: [Caching](), [Redis](), [Embeddings](), [Large Language Model](), [Inference]() Tags: [cache](), [caching](), [embeddings](), [inference](), [llm](), [redis]() ### AI overview Production LLM applications can reduce repeated model calls by caching generated responses and matching new questions to prior questions using embeddings. The article discusses Redis LangCache, including similarity thresholds, expiration, data isolation, monitoring, and an example where a cache hit was roughly 6x faster than direct inference. ### Source excerpt What production agents must preserve between turns, and what they must reset. ## Your Agent Harness Needs Runtime Security DevFeed: [Your Agent Harness Needs Runtime Security]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-09T20:59:58Z Content type: tutorial Language: en Sources: [Daily Dose of Data Science]() Topics: [agent observability](), [Agent Harness](), [Security](), [Open Source](), [telemetry]() Tags: [agent](), [agent-harness](), [ai-agents](), [anthropic](), [claude](), [cybersecurity](), [github](), [guide](), [local](), [monitoring](), [open-source](), [security](), [telemetry]() ### AI overview This guide presents Agent Beacon, an open-source telemetry layer for AI agents. It records tool calls, shell commands, file changes, and approval decisions as structured runtime events across supported agent harnesses, providing a live record of agent behavior for security monitoring and investigation. ### Source excerpt A 100% local, open-source guide to recording what AI agents actually do at runtime. ## Momentum in ML, Explained Visually and Intuitively! DevFeed: [Momentum in ML, Explained Visually and Intuitively!]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-08T21:24:18Z Content type: article Language: en Sources: [Daily Dose of Data Science]() Topics: [Machine learning](), [Optimization]() Tags: [ml](), [optimization]() ### AI overview This article explains momentum in machine learning visually and intuitively, presenting it as an optimization technique for speeding model training. The supplied excerpt also previews related coverage of distributed training and hyperparameter optimization. ### Source excerpt (a popular ML interview question) ## LLM Routing Can Cost More Than Not Routing DevFeed: [LLM Routing Can Cost More Than Not Routing]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-07T20:30:58Z Content type: article Language: en Sources: [Daily Dose of Data Science]() Topics: [Model Routing](), [Large Language Model](), [Frontier Model](), [coding]() Tags: [agent](), [cost](), [llm](), [model](), [models](), [routing]() ### AI overview The article examines why routing requests among LLMs can cost more than using one model throughout an agent session. Although cheaper models may handle simpler tasks, routing adds overhead and can be counterproductive inside agent loops. ### Source excerpt ...covered with a production-grade router for LLM apps. ## KV Cache Engineering for LLM Serving DevFeed: [KV Cache Engineering for LLM Serving]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-06T20:43:32Z Content type: tutorial Language: en Sources: [Daily Dose of Data Science]() Topics: [Caching](), [Large Language Model](), [LLM Techniques](), [GPU](), [Inference](), [llama](), [quantization]() Tags: [cache](), [engineering](), [gpu](), [inference](), [llama](), [llm](), [llmops](), [quantization]() ### AI overview This article explains how KV cache growth affects GPU memory and attention costs during LLM serving. It organizes twelve optimization techniques by whether they reduce heads, layers, retained tokens, representation width, precision, state size, allocation waste, or duplicate memory, while noting the trade-offs and limits of each approach. ### Source excerpt 12 techniques to manage KV cache in production. ## 5 Embedding Compression Techniques DevFeed: [5 Embedding Compression Techniques]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-04T20:51:57Z Content type: tutorial Language: en Sources: [Daily Dose of Data Science]() Topics: [Compression](), [Embeddings](), [quantization](), [Inference]() Tags: [compression](), [embedding](), [inference](), [quantization](), [vector]() ### AI overview A tutorial explaining five embedding compression techniques: PCA, Matryoshka Representation Learning, scalar quantization, binary quantization, and Product Quantization. It describes how they reduce dimensions or per-value precision and how rescoring can improve ranking after compressed retrieval. ### Source excerpt ...explained visually. ## Attention Mechanisms in LLMs, clearly explained DevFeed: [Attention Mechanisms in LLMs, clearly explained]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-03T20:05:32Z Content type: tutorial Language: en Sources: [Daily Dose of Data Science]() Topics: [Large Language Model](), [Cache]() Tags: [cache](), [llms](), [tokens]() ### AI overview A tutorial explaining why attention is used in language models, how long-range dependencies are handled, and why storing attention state for long sequences and large batches can exhaust GPU memory. It introduces attention variants including Multi-Query Attention, Grouped-Query Attention, and Multi-Head Latent Attention. ### Source excerpt Everything you need to understand how attention works, why the KV cache is the bottleneck, and what every attention variant is actually solving. ## Choosing Local Models for Coding Agents Based on Hardware and Workload DevFeed: [Choosing Local Models for Coding Agents Based on Hardware and Workload]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-02T19:10:34Z Content type: tutorial Language: en Sources: [Daily Dose of Data Science]() Topics: [Local AI](), [Hardware](), [Artificial Intelligence](), [Inference](), [quantization](), [Open Source]() Tags: [ai](), [hardware](), [local](), [local-ai](), [model](), [open-source](), [quantization](), [run]() ### AI overview This practitioner's guide explains why local models that work well for chat may perform poorly in coding-agent workloads. It discusses growing conversation context, memory requirements, precision, sustained speed, and thermal limits, then introduces Magnitude, an open-source inference server that profiles a machine and selects a configuration for local agent use. ### Source excerpt A practitioner's guide to local AI. ## Deploying a RAG Chatbot with Shared State and Storage Across Replicas DevFeed: [Deploying a RAG Chatbot with Shared State and Storage Across Replicas]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-01T21:11:23Z Content type: tutorial Language: en Sources: [Daily Dose of Data Science]() Topics: [Retrieval-Augmented Generation](), [Kubernetes](), [Terraform](), [FastAPI](), [LangChain](), [Python]() Tags: [fastapi](), [github](), [persistence](), [pgvector](), [python](), [rag](), [retrieval](), [terraform]() ### AI overview The article explains why a RAG chatbot that works locally can lose vector indexes, conversation history, and documents when deployed across multiple replicas. It recommends shared persistence for embeddings, checkpointed conversation state, and shared object storage, with examples using Postgres, pgvector, LangGraph, and object storage. ### Source excerpt + a popular LLM interview question. ## WebMCP: A Browser API for Exposing Website Actions to AI Agents DevFeed: [WebMCP: A Browser API for Exposing Website Actions to AI Agents]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-08-31T13:43:15Z Content type: article Language: en Sources: [Daily Dose of Data Science]() Topics: [browser](), [Chrome](), [Edge](), [Artificial Intelligence]() Tags: [agent](), [ai](), [browser](), [chrome](), [edge]() ### AI overview The article explains WebMCP, a browser API from the Chrome and Edge teams that allows websites to expose actions such as search, cart, checkout, and booking flows to AI agents. It contrasts this approach with screenshot-based navigation, which can be slower and fragile when page layouts change. ### Source excerpt Everything you need to understand WebMCP and expose your site's actions to an agent. ## Why KV Cache Stores K and V Vectors But Never Q? DevFeed: [Why KV Cache Stores K and V Vectors But Never Q?]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-08-30T20:15:33Z Content type: article Language: en Sources: [Daily Dose of Data Science]() Topics: [LLMs](), [Parsing](), [Inference]() Tags: [gpu](), [interview](), [llms](), [parsing](), [pdf](), [technical]() ### AI overview The document discusses Marker v2, an open-source PDF parsing pipeline that uses shared inference serving and batching to improve GPU utilization. It also begins explaining autoregressive LLMs and why their forward pass is relevant to KV-cache behavior, but the supplied text ends before the explanation is complete. ### Source excerpt A popular technical LLM interview question. ## Explicit Task State Enables Incremental Updates in Long Analysis Pipelines DevFeed: [Explicit Task State Enables Incremental Updates in Long Analysis Pipelines]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-08-28T21:11:08Z Content type: article Language: en Sources: [Daily Dose of Data Science]() Topics: [Artificial Intelligence](), [Code](), [Open Source](), [Command-line interface](), [Text-based user interface](), [systems]() Tags: [ai](), [code](), [command-line](), [open-source](), [state](), [state-management](), [systems]() ### AI overview The article explains how explicit task state can make long analysis pipelines responsive to changing requirements. By tracking plans, completed steps, artifacts, dependencies, and exceptions outside the conversation, a system can preserve valid work and replan only affected downstream steps. It describes Apodex 1.1, Deep Discover, and the open-source FrontierAgent runtime as examples of this approach. ### Source excerpt Full guide with code. ## KV vs Prefix vs Prompt vs Semantic Caching DevFeed: [KV vs Prefix vs Prompt vs Semantic Caching]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-08-27T20:01:47Z Content type: article Language: en Sources: [Daily Dose of Data Science]() Topics: [Caching](), [Large Language Model](), [Neo4j]() Tags: [caching](), [embedding](), [knowledge-graph](), [latency](), [llm](), [memory](), [nvme](), [object-storage](), [retrieval](), [server](), [token](), [vector]() ### AI overview The article distinguishes KV caching, prefix caching, prompt caching, and semantic caching in LLM systems. It explains what each cache stores, how exact-match and fuzzy-match behavior differ, and how cache misses affect cost, latency, and correctness. It also describes Konig's tiered storage approach for many small knowledge graphs, though the supplied text is truncated. ### Source excerpt ...explained with best practices in production. ## \[Hands-on\] Turn Scientific Figures Into Structured Data with Mistral OCR DevFeed: [\[Hands-on\] Turn Scientific Figures Into Structured Data with Mistral OCR]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-08-26T21:06:26Z Content type: tutorial Language: en Sources: [Daily Dose of Data Science]() Topics: [Artificial Intelligence](), [Routing (disambiguation)](), [incident](), [context window](), [FIRST](), [Google](), [SDKs]() Tags: [code](), [mistral](), [ocr]() ### AI overview The supplied excerpts discuss coordinating multiple agents and people through shared channels. They describe the limits of role-based handoffs, including duplicated work, lost context, and invisible negative results, and present Switch as a way to preserve shared reports and threads. The title and body appear to describe different subjects. ### Source excerpt A full walkthrough of the extraction schema, with code. ## Build a Multi-Agent GTM Intelligence System DevFeed: [Build a Multi-Agent GTM Intelligence System]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-08-25T20:26:56Z Content type: tutorial Language: en Sources: [Daily Dose of Data Science]() Topics: [Code](), [API]() Tags: [agent](), [api](), [building](), [code](), [multi-agent](), [pipelines](), [research]() ### AI overview A hands-on tutorial for building a multi-agent go-to-market intelligence pipeline with Seltz. It explains how combining structured people and company-news records can help identify timely re-engagement opportunities. ### Source excerpt ...explained with code. ## Preloading Knowledge Into a Model Instead of Retrieving It DevFeed: [Preloading Knowledge Into a Model Instead of Retrieving It]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-08-24T17:13:39Z Content type: tutorial Language: en Sources: [Daily Dose of Data Science]() Topics: [Retrieval Augmented Generation (RAG)](), [Caching](), [long-context](), [Inference](), [Self-hosted](), [model-deployment](), [GPU]() Tags: [caching](), [compute](), [context-window](), [deployment](), [inference](), [rag](), [retrieval](), [self-hosted](), [storage]() ### AI overview This article introduces a three-part RAG Systems course about preloading a knowledge corpus into a model's stored KV cache so subsequent queries can skip retrieval, chunking, and embedding. It covers naive, compressed, modular, and trained preloading, along with context limits, provider and self-hosted economics, cache compression constraints, and production deployment. ### Source excerpt How to process your corpus once, skip retrieval entirely, and serve every query from a stored cache. Three parts covering the full spectrum. ## How Semantic Code Navigation Cuts Agent Token Costs by up to 36% DevFeed: [How Semantic Code Navigation Cuts Agent Token Costs by up to 36%]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-08-21T21:51:15Z Content type: article Language: en Sources: [Daily Dose of Data Science]() Topics: [coding](), [ai-coding](), [Code]() Tags: [agent](), [ai](), [ai-coding](), [code](), [coding](), [writing-code]() ### AI overview The article argues that coding agents spend substantial tokens finding where changes belong in a codebase before writing code. It examines semantic code navigation as a way to reduce that discovery cost, with a stated reduction of up to 36%. ### Source excerpt Understanding what an agent actually does with the tokens before it writes code.