Machine Learning Guide

Machine Learning Guide

OCDevel
Country USA
Language EN-US
Episodes 60
Latest 26.02.2026

Machine Learning Guide is an audio course that teaches the fundamentals of machine learning and artificial intelligence. It covers intuition, models (shallow and deep), math, languages, and frameworks. The podcast aims to provide a high-level overview, acting as a syllabus with curated resources for each episode. It is designed to be a supplement during exercise, commute, or chores.

Episodes

  • MLA 030 AI and Programming Jobs in 2026
    MLA 030 AI and Programming Jobs in 2026 26.02.2026 31m
    AI and programming jobs in 2026: unemployment held and software postings are recovering, but entry-level hiring narrowed and the growth went senior. Why cheap code made specs, verification and domain knowledge scarce, where AI jobs grew, and what to learn and show. Links Notes and resources at ocdevel.com/mlg/mla-30 Join the free MLG group: listen to my other AI shows, ask me questions, and talk with other listeners Will AI replace programmers? Not in aggregate so far. US unemployment was 4.1% in October 2026, in a 4.1–4.3% range since March. What changed is who gets hired. Stanford's Canaries...
  • MLA 029 Is OpenClaw Safe? Uses and Alternatives
    MLA 029 Is OpenClaw Safe? Uses and Alternatives 22.02.2026 32m
    OpenClaw in 2026 is safe for read-only jobs on its own machine and accounts, not as a full-access assistant logged in as you. What it's for, how to harden it and vet skills, what it costs, and the alternatives: Hermes Agent, Gemini Spark and OpenAI's dots. Links Notes and resources at ocdevel.com/mlg/mla-29 Join the free MLG group: listen to my other AI shows, ask me questions, and talk with other listeners What is OpenClaw? An open-source, self-hosted personal agent: an always-on agent loop (MLA 28) that you message from a chat app, with access to your files, shell, browser and accounts. Pete...
  • MLA 028 How to Build an AI Agent in 2026
    MLA 028 How to Build an AI Agent in 2026 22.02.2026 33m
    An AI agent is a model running tools in a loop toward a goal, and you build one in order: one call, then tools, the loop and evals. Also: frameworks, MCP vs A2A, memory, multi-agent patterns, prompt injection and cost. Links Notes and resources at ocdevel.com/mlg/mla-28 Join the free MLG group: listen to my other AI shows, ask me questions, and talk with other listeners What is an AI agent? A model running tools in a loop toward a goal: model + tools + loop + stop condition (done, turn cap, budget cap, or a human). In a workflow your code decides the next step; in an agent the model does. Codi...
  • MLA 027 AI Voice, Music and Media Pipelines
    MLA 027 AI Voice, Music and Media Pipelines 14.07.2025 32m
    The AI media pipeline: ElevenLabs v4 or Gemini for voice, licensed music over Suno, ComfyUI once a job repeats, and fal or Replicate queues for APIs. Also voice-cloning law, upscaling, captions, loudness targets, and EU and YouTube labeling rules. Links Notes and resources at ocdevel.com/mlg/mla-27 Join the free MLG group: listen to my other AI shows, ask me questions, and talk with other listeners The AI media pipeline script → narration → images and clips (MLA 25, MLA 26) → music and sound effects → edit → upscale → captions → loudness → export → label and upload Best AI voice generator Elev...
  • MLA 026 Best AI Video Generators in 2026
    MLA 026 Best AI Video Generators in 2026 12.07.2025 30m
    AI video generation in 2026 has no single winner: Gemini Omni, Wan 3, Seedance 2.5 and MiniMax H3 models are near-tied, Kling 4 leads on control, and Sora is gone. It also covers Runway as a multi-model host, image-to-video, consistency, editing, avatars, cost per minute and free options. Links Notes and resources at ocdevel.com/mlg/mla-26 Join the free MLG group: listen to my other AI shows, ask me questions, and talk with other listeners What happened to Sora OpenAI closed the Sora app on April 26, 2026 and the API on September 24, 2026. Its deprecation page lists "no one-to-one replacement....
  • MLA 025 Best AI Image Generators in 2026
    MLA 025 Best AI Image Generators in 2026 09.07.2025 29m
    The best AI image generator in 2026 by blind votes is GPT Image 2.6, but Nano Banana 2.1 costs a sixth as much and Flux 3 Klein runs on your own GPU. It also covers editing and prompting, text in images, consistent characters, open-weight licenses and commercial use by tool. Links Notes and resources at ocdevel.com/mlg/mla-25 Join the free MLG group: listen to my other AI shows, ask me questions, and talk with other listeners Best AI image generator in 2026 OpenAI's GPT Image 2.6 (ChatGPT Images 2.6, November 4, 2026) leads on blind human votes: the top five slots on the Artificial Analysis te...
  • MLG 036 Autoencoders
    MLG 036 Autoencoders 30.05.2025 1h 5m
    Auto encoders are neural networks that compress data into a smaller "code," enabling dimensionality reduction, data cleaning, and lossy compression by reconstructing original inputs from this code. Advanced auto encoder types, such as denoising, sparse, and variational auto encoders, extend these concepts for applications in generative modeling, interpretability, and synthetic data generation. Links Notes and resources at ocdevel.com/mlg/36 Try a walking desk - stay healthy & sharp while you learn & code Build the future of multi-agent software with AGNTCY. Thanks to T.J. Wilder from intrep.io...
  • MLG 035 Large Language Models 2
    MLG 035 Large Language Models 2 08.05.2025 45m
    At inference, large language models use in-context learning with zero-, one-, or few-shot examples to perform new tasks without weight updates, and can be grounded with Retrieval Augmented Generation (RAG) by embedding documents into vector databases for real-time factual lookup using cosine similarity. LLM agents autonomously plan, act, and use external tools via orchestrated loops with persistent memory, while recent benchmarks like GPQA (STEM reasoning), SWE Bench (agentic coding), and MMMU (multimodal college-level tasks) test performance alongside prompt engineering techniques such as cha...
  • MLG 034 Large Language Models 1
    MLG 034 Large Language Models 1 07.05.2025 50m
    Explains language models (LLMs) advancements. Scaling laws - the relationships among model size, data size, and compute - and how emergent abilities such as in-context learning, multi-step reasoning, and instruction following arise once certain scaling thresholds are crossed. The evolution of the transformer architecture with Mixture of Experts (MoE), describes the three-phase training process culminating in Reinforcement Learning from Human Feedback (RLHF) for model alignment, and explores advanced reasoning techniques such as chain-of-thought prompting which significantly improve complex tas...
  • MLA 024 Agentic Coding: Specs and Review
    MLA 024 Agentic Coding: Specs and Review 13.04.2025 31m
    Agentic coding best practices: write a spec, make the agent plan, verify with checks it must run, and review with a fresh model before you merge. Also: parallel agents, auto mode safety, and what studies show about speed. Links Notes and resources at ocdevel.com/mlg/mla-24 Join the free MLG group: listen to my other AI shows, ask me questions, and talk with other listeners Agentic coding best practices spec → plan → implement in slices → verify → review → human merge Writing code is cheap; checking it is the job. Anthropic's and OpenAI's Codex guides both describe this loop. How detailed shoul...
  • MLA 023 Inside a Coding Agent: Skills, Hooks, MCP
    MLA 023 Inside a Coding Agent: Skills, Hooks, MCP 13.04.2025 31m
    Inside a coding agent: context is the budget, skills load on demand, hooks enforce rules, subagents get fresh windows and MCP tools cost tokens. What belongs in CLAUDE.md, and the settings that guard against a PocketOS-style deletion. Links Notes and resources at ocdevel.com/mlg/mla-23 Join the free MLG group: listen to my other AI shows, ask me questions, and talk with other listeners How a coding agent uses its context window Each turn sends the whole conversation back to the model, so every file read and test log stays in the window until you compact or clear. The instruction file, skill de...
  • MLA 022 Claude Code vs Codex vs Cursor in 2026
    MLA 022 Claude Code vs Codex vs Cursor in 2026 09.02.2025 29m
    Vibe coding in 2026 means picking an agent: Claude Code for steering, Codex for delegation, Cursor for editors, Antigravity for Google users. Plus pricing and free tiers, which model to run, OpenCode and DeepSeek or Kimi, and no-code builders. Links Notes and resources at ocdevel.com/mlg/mla-22 Join the free MLG group: listen to my other AI shows, ask me questions, and talk with other listeners What is vibe coding? Building software with an AI model without reviewing the code it writes. Andrej Karpathy coined it in February 2025 for "throwaway weekend projects". Fine for prototypes; code that...
  • MLG 033 Transformers
    MLG 033 Transformers 09.02.2025 43m
    Links: Notes and resources at ocdevel.com/mlg/33 3Blue1Brown videos: https://3blue1brown.com/ Try a walking desk stay healthy & sharp while you learn & code Try Descript audio/video editing with AI power-tools Background & Motivation RNN Limitations: Sequential processing prevents full parallelization—even with attention tweaks—making them inefficient on modern hardware. Breakthrough: "Attention Is All You Need" replaced recurrence with self-attention, unlocking massive parallelism and scalability. Core Architecture Layer Stack: Consists of alternating self-attention and feed-forward (MLP) lay...
  • MLA 021 Databricks: Cloud Analytics and MLOps
    MLA 021 Databricks: Cloud Analytics and MLOps 22.06.2022 26m
    Databricks is a cloud-based platform for data analytics and machine learning operations, integrating features such as a hosted Spark cluster, Python notebook execution, Delta Lake for data management, and seamless IDE connectivity. Raybeam utilizes Databricks and other ML Ops tools according to client infrastructure, scaling needs, and project goals, favoring Databricks for its balanced feature set, ease of use, and support for both startups and enterprises. Links Notes and resources at ocdevel.com/mlg/mla-21 Try a walking desk stay healthy & sharp while you learn & code Raybeam and Databricks...
  • MLA 020 Kubeflow and ML Pipeline Orchestration on Kubernetes
    MLA 020 Kubeflow and ML Pipeline Orchestration on Kubernetes 29.01.2022 1h 8m
    Machine learning pipeline orchestration tools, such as SageMaker and Kubeflow, streamline the end-to-end process of data ingestion, model training, deployment, and monitoring, with Kubeflow providing an open-source, cross-cloud platform built atop Kubernetes. Organizations typically choose between cloud-native managed services and open-source solutions based on required flexibility, scalability, integration with existing cloud environments, and vendor lock-in considerations. Links Notes and resources at ocdevel.com/mlg/mla-20 Try a walking desk stay healthy & sharp while you learn & code Dirk-...
  • MLA 019 Cloud, DevOps & Architecture
    MLA 019 Cloud, DevOps & Architecture 13.01.2022 1h 15m
    The deployment of machine learning models for real-world use involves a sequence of cloud services and architectural choices, where machine learning expertise must be complemented by DevOps and architecture skills, often requiring collaboration with professionals. Key concepts discussed include infrastructure as code, cloud container orchestration, and the distinction between DevOps and architecture, as well as practical advice for machine learning engineers wanting to deploy products securely and efficiently. Links Notes and resources at ocdevel.com/mlg/mla-19 Try a walking desk stay healthy...
  • MLA 017 AWS Local Development Environment
    MLA 017 AWS Local Development Environment 06.11.2021 1h 4m
    AWS development environments for local and cloud deployment can differ significantly, leading to extra complexity and setup during cloud migration. By developing directly within AWS environments, using tools such as Lambda, Cloud9, SageMaker Studio, client VPN connections, or LocalStack, developers can streamline transitions to production and leverage AWS-managed services from the start. This episode outlines three primary strategies for treating AWS as your development environment, details the benefits and tradeoffs of each, and explains the role of infrastructure-as-code tools such as Terraf...
  • MLA 016 AWS SageMaker MLOps 2
    MLA 016 AWS SageMaker MLOps 2 05.11.2021 1h
    SageMaker streamlines machine learning workflows by enabling integrated model training, tuning, deployment, monitoring, and pipeline automation within the AWS ecosystem, offering scalable compute options and flexible development environments. Cloud-native AWS machine learning services such as Comprehend and Poly provide off-the-shelf solutions for NLP, time series, recommendations, and more, reducing the need for custom model implementation and deployment. Links Notes and resources at ocdevel.com/mlg/mla-16 Try a walking desk stay healthy & sharp while you learn & code Model Training and Tunin...
  • MLA 015 AWS SageMaker MLOps 1
    MLA 015 AWS SageMaker MLOps 1 04.11.2021 47m
    SageMaker is an end-to-end machine learning platform on AWS that covers every stage of the ML lifecycle, including data ingestion, preparation, training, deployment, monitoring, and bias detection. The platform offers integrated tools such as Data Wrangler, Feature Store, Ground Truth, Clarify, Autopilot, and distributed training to enable scalable, automated, and accessible machine learning operations for both tabular and large data sets. Links Notes and resources at ocdevel.com/mlg/mla-15 Try a walking desk stay healthy & sharp while you learn & code Amazon SageMaker: The Machine Learning Op...
  • MLA 014 Deploying ML in 2026: APIs vs Self-Hosting
    MLA 014 Deploying ML in 2026: APIs vs Self-Hosting 18.01.2021 32m
    Hosting and deploying ML in 2026 starts with an API: move to serverless GPUs, rented GPUs or Spot only when volume, compliance, latency or model availability forces it. Also covers cold starts, vLLM vs SGLang vs llama.cpp vs Ollama, quantization, batch and caching discounts, and tracing. Links Notes and resources at ocdevel.com/mlg/mla-14 Join the free MLG group: listen to my other AI shows, ask me questions, and talk with other listeners Should I self-host an LLM or call an API? Call an API until one of four things applies: sustained volume, a compliance rule, a latency floor, or a model that...

Popular in

The podcast also appears in the podcast charts of these countries.