#010 Building Robust AI and Data Systems, Data Architecture, Data Quality, Data Storage

How AI Is Built

Player FM - Internet Radio Done Right

הוסף לפני one שנה

תוכן מסופק על ידי Nicolay Gerold. כל תוכן הפודקאסטים כולל פרקים, גרפיקה ותיאורי פודקאסטים מועלים ומסופקים ישירות על ידי Nicolay Gerold או שותף פלטפורמת הפודקאסט שלהם. אם אתה מאמין שמישהו משתמש ביצירה שלך המוגנת בזכויות יוצרים ללא רשותך, אתה יכול לעקוב אחר התהליך המתואר כאן https://he.player.fm/legal.

Everyday AI Podcast – An AI and ChatGPT Podcast

1
EP 570: ChatGPT’s Agent Mode Overview: 5 things you should know 32:40

לפני 3 ימים32:40

הפעל מאוחר יותר

רשימות

לייק

אהבתי

32:40

ChatGPT Agent is here! ↳ What the heck is it? ↳ How does it work? ↳ What do you need to know? Glad you asked, shorties. Join us for the answers. Square keeps up so you don't have to slow down. Get everything you need to run and grow your business—without any long-term commitments. And why wait? Right now, you can get up to $200 off Square hardware at square.com/go/jordan. Run your business smarter with Square. Get started today. Newsletter: Sign up for our free daily newsletter More on this Episode: Episode Page Join the discussion: Thoughts on this? Join the convo and connect with other AI leaders on LinkedIn. Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup Website: YourEverydayAI.com Email The Show: info@youreverydayai.com Connect with Jordan on LinkedIn Topics Covered in This Episode: ChatGPT Agent Mode Overview & Naming Live ChatGPT Agent Demo Walkthrough ChatGPT Agent Mode Availability & Pricing Operator vs. Deep Research Capabilities Explained ChatGPT Agent Virtual Computer Functions Spreadsheet and PowerPoint Generation in ChatGPT Mini RAG-Ready Agents with Data Connectors ChatGPT Agent Security and Biological Risk Classification Timestamps: 00:00 "Introducing ChatGPT Agent" 03:41 Potential Delay for Paid Plan Rollout 09:24 "Chat GPT Agent: New Tools Overview" 12:44 OpenAI-Microsoft Tensions Over Software Overlap 16:42 "ChatGPT's New RAG Feature Unveiled" 21:55 AI Agent with Weapon Risk 23:31 Agent Models: Boon or Bane? 29:05 "Agent Mode: Seamless Editing Integration" Keywords: ChatGPT Agent, Agent Mode, OpenAI, virtual computer, Agentic skills, Operator, Deep Research, browsing websites, web research, synthesizing information, Microsoft competitor, PowerPoint creation, Excel spreadsheet creation, terminal access, public API integration, connectors, data analysis, image generation, multi-agent environments, retrieval augmented generation, mini RAG, AI operating system, human-in-the-loop, security concerns, biology classifier, biological weapons classification, chemical weapons classification, O3 model, Google Gemini 2.5 Pro, agentic models, AI workflows, editable slide deck, Microsoft Office alternative, AI-powered presentations, spreadsheet automation, cloud-based agents, AI task automation, calendar integration, Gmail connector, Google Drive connector, Outlook connector, team collaboration, premium AI features, desktop to browser transition, file creation, terminal commands, workflow automation Send Everyday AI and Jordan a text message. (We can't reply back unless you leave contact info) Try Gemini 2.5 Flash! Sign up at AIStudio.google.com to get started.…

לפני שנה 45:32

MP3•בית הפרקים

Summary by Section

Introduction

Anjan Banerjee, a data architect, discusses building complex AI and data systems
Explains the basics of data architecture using Lego and chat app examples

Sources and Tools

Identifying data sources is the first step in designing a data architecture
Pick the right tools to extract data based on use cases (block storage for images, time series DB, etc.)
Use one tool for most activities if possible, but specialized tools offer benefits
Multi-modal storage engines are gaining popularity (Snowflake, Databricks, BigQuery)

Airflow and Orchestration

Airflow is versatile but has a learning curve; good for orgs with Python/data engineering skills
For less technical orgs, GUI-based tools like Talend, Alteryx may be better
AWS Step Functions and managed Airflow are improving native orchestration capabilities
For multi-cloud, prefer platform-agnostic tools like Astronomer, Prefect, Airbyte

AI and Data Processing

ML is key for data-intensive use cases to avoid storing/processing petabytes in cloud
TinyML and edge computing enable ML inference on device (drones, manufacturing)
Cloud batch processing still dominates for user targeting, recommendations

Data Lakes and Storage

Storage choice depends on data types, use cases, cloud ecosystem
Delta Lake excels at data versioning and consistency; Iceberg at partitioning and metadata
Pulling data into separate system often needed for advanced analytics beyond source system

Data Quality and Standardization

"Poka-yoke" error-proofing of input screens is vital for downstream data quality
Impose data quality rules and unified schemas (e.g. UTC timestamps) during ingestion
Complexity arises with multi-region compliance (GDPR, CCPA) requiring encryption, sanitization

Hot Takes and Wishes

Snowflake is overhyped; great UX but costly at scale. Databricks is preferred.
Automated data set joining and entity resolution across systems would be a game-changer

Anjan Banerjee:

Nicolay Gerold:

00:00 Understanding Data Architecture

12:36 Choosing the Right Tools

20:36 The Benefits of Serverless Functions

21:34 Integrating AI in Data Acquisition

24:31 The Trend Towards Single Node Engines

26:51 Choosing the Right Database Management System and Storage

29:45 Adding Additional Storage Components

32:35 Reducing Human Errors for Better Data Quality

39:07 Overhyped and Underutilized Tools

Data architecture, AI, data systems, data sources, data extraction, data storage, multi-modal storage engines, data orchestration, Airflow, edge computing, batch processing, data lakes, Delta Lake, Iceberg, data quality, standardization, poka-yoke, compliance, entity resolution

59 פרקים

#Tech #Nicolay Gerold #Technology #Llm #Machine Learning #Data Engineering

How AI Is Built

#010 Building Robust AI and Data Systems, Data Architecture, Data Quality, Data Storage

How AI Is Built

published לפני שנה

שתפו

MP3•בית הפרקים

Summary by Section

Introduction

Anjan Banerjee, a data architect, discusses building complex AI and data systems
Explains the basics of data architecture using Lego and chat app examples

Sources and Tools

Identifying data sources is the first step in designing a data architecture
Pick the right tools to extract data based on use cases (block storage for images, time series DB, etc.)
Use one tool for most activities if possible, but specialized tools offer benefits
Multi-modal storage engines are gaining popularity (Snowflake, Databricks, BigQuery)

Airflow and Orchestration

Airflow is versatile but has a learning curve; good for orgs with Python/data engineering skills
For less technical orgs, GUI-based tools like Talend, Alteryx may be better
AWS Step Functions and managed Airflow are improving native orchestration capabilities
For multi-cloud, prefer platform-agnostic tools like Astronomer, Prefect, Airbyte

AI and Data Processing

ML is key for data-intensive use cases to avoid storing/processing petabytes in cloud
TinyML and edge computing enable ML inference on device (drones, manufacturing)
Cloud batch processing still dominates for user targeting, recommendations

Data Lakes and Storage

Storage choice depends on data types, use cases, cloud ecosystem
Delta Lake excels at data versioning and consistency; Iceberg at partitioning and metadata
Pulling data into separate system often needed for advanced analytics beyond source system

Data Quality and Standardization

"Poka-yoke" error-proofing of input screens is vital for downstream data quality
Impose data quality rules and unified schemas (e.g. UTC timestamps) during ingestion
Complexity arises with multi-region compliance (GDPR, CCPA) requiring encryption, sanitization

Hot Takes and Wishes

Snowflake is overhyped; great UX but costly at scale. Databricks is preferred.
Automated data set joining and entity resolution across systems would be a game-changer

Anjan Banerjee:

Nicolay Gerold:

00:00 Understanding Data Architecture

12:36 Choosing the Right Tools

20:36 The Benefits of Serverless Functions

21:34 Integrating AI in Data Acquisition

24:31 The Trend Towards Single Node Engines

26:51 Choosing the Right Database Management System and Storage

29:45 Adding Additional Storage Components

32:35 Reducing Human Errors for Better Data Quality

39:07 Overhyped and Underutilized Tools

59 פרקים

#Tech #Nicolay Gerold #Technology #Llm #Machine Learning #Data Engineering

כל הפרקים

How AI Is Built

1
#052 Don't Build Models, Build Systems That Build Models 59:22

לפני 20 ימים59:22

59:22

Nicolay here, Today I have the chance to talk to Charles from Modal, who went from doing a PhD on neural network optimization in the 2010s - when ML engineers could build models with a soldering iron and some sticks - to architecting serverless infrastructure for AI models. Modal is about removing barriers so anyone can spin up a hundred GPUs in seconds. The critical insight that stuck with me: "Don't build models, build systems that build models." Organizations often make the mistake of celebrating a one-time fine-tuned model that matches GPT-4 performance only to watch it become obsolete when the next foundation model arrives - typically three to six months down the road. Charles's approach to infrastructure is particularly unconventional. He argues that serverless isn't just about convenience - it fundamentally changes how ambitious you can be with scale. "There's so much that gets in the way of trying to spin up a hundred GPUs or a thousand CPU containers that people just don't think to do something big." The winning approach involves automated data pipelines with feedback collection, continuous evaluation against new foundation models, AB testing and canary deployments, and systematic error analysis and retraining. In the podcast, we also cover: Why inference, not training, is where the money is made How to rethink compute when moving from traditional cloud to serverless The economics of automated resource management Why task decomposition is the key ML engineering skill When to earn the right to fine-tune versus using foundation models *📶 Connect with Charles:* Twitter - https://twitter.com/charlesirl Modal Labs - https://modal.com Modal Slack Community - https://modal.com/slack *📶 Connect with Nicolay:* LinkedIn - https://linkedin.com/in/nicolay-gerold/ X / Twitter - https://x.com/nicolaygerold Bluesky - https://bsky.app/profile/nicolaygerold.com Website - https://nicolaygerold.com/ My Agency Aisbach - https://aisbach.com/ (for ai implementations / strategy) *⏱️ Important Moments* From CUDA to Serverless : [00:01:38] Charles's journey from PhD neural network optimization to building Modal's serverless infrastructure. Rethinking Scale Ambition : [00:01:38] "There's so much that gets in the way of trying to spin up a hundred GPUs that people just don't think to do something big." The Economics of Serverless : [00:04:09] How automated resource management changes the cattle vs pets paradigm for GPU workloads. Lambda vs Modal Philosophy : [00:04:20] Why Modal was designed for tasks that take bytes and emit megabytes, unlike Lambda's middleware focus. Inference Economics Reality : [00:10:16] "Almost nobody gets paid to make models - organizations get paid to make predictions." The Open Source Commoditization : [00:14:55] How foundation models are becoming undifferentiated capabilities like databases. Task Decomposition as Core Skill : [00:22:00] Why breaking down problems is equivalent to recognizing API boundaries in software engineering. Systems That Build Models : [00:33:31] The critical difference between delivering static weights versus repeatable model production systems Earning the Right to Fine-Tune : [00:34:06] The infrastructure prerequisites needed before attempting model customization. Multi-Node Training Challenges : [00:52:24] How serverless platforms handle the contradiction of high-performance computing with spiky demand. *🛠️ Tools & Tech Mentioned* Modal - https://modal.com (serverless GPU infrastructure) AWS Lambda - https://aws.amazon.com/lambda/ (traditional serverless) Kubernetes - https://kubernetes.io/ (container orchestration) Temporal - https://temporal.io/ (workflow orchestration) Weights & Biases - https://wandb.ai/ (experiment tracking) Hugging Face - https://huggingface.co/ (model repository) PyTorch Distributed - https://pytorch.org/tutorials/intermediate/ddp_tutorial.html (multi-GPU training) Redis - https://redis.io/ (caching and queues) *📚 Recommended Resources* Full Stack Deep Learning - https://fullstackdeeplearning.com/ (deployment best practices) Modal Documentation - https://modal.com/docs (getting started guide) Deep Seek Paper - https://arxiv.org/abs/2401.02954 (disaggregated inference patterns) AI Engineer Summit - https://ai.engineer/ (community events) MLOps Community - https://mlops.community/ (best practices) 💬 Join The Conversation Follow How AI Is Built on YouTube - https://youtube.com/@howaiisbuilt , Bluesky - https://bsky.app/profile/howaiisbuilt.fm , or Spotify - https://open.spotify.com/show/3hhSTyHSgKPVC4sw3H0NUc?_authfailed=1%29 If you have any suggestions for future guests, feel free to leave it in the comments or write me (Nicolay) directly on LinkedIn - https://linkedin.com/in/nicolay-gerold/ , X - https://x.com/nicolaygerold, or Bluesky - https://bsky.app/profile/nicolaygerold.com . Or at nicolay.gerold@gmail.com . I will be opening a Discord soon to get you guys more involved in the episodes! Stay tuned for that.…

How AI Is Built

1
#051 Build systems that can be debugged at 4am by tired humans with no context 1:05:51

לפני 5 weeks1:05:51

1:05:51

Nicolay here, Today I have the chance to talk to Charity Majors, CEO and co-founder of Honeycomb, who recently has been writing about the cost crisis in observability. "Your source of truth is production, not your IDE - and if you can't understand your code there, you're flying blind." The key insight is architecturally simple but operationally transformative: replace your 10-20 observability tools with wide structured events that capture everything about a request in one place. Most teams store the same request data across metrics, logs, traces, APM, and error tracking - creating a 20X cost multiplier while making debugging nearly impossible because you're reconstructing stories from fragments. Charity's approach flips this: instrument once with rich context, derive everything else from that single source. This isn't just about cost - it's about giving engineers the connective tissue to understand distributed systems. When you can correlate "all requests failing from Android version X in region Y using language pack Z," you find problems in minutes instead of days. The second is putting developers on call for their own code. This creates the tight feedback loop that makes engineers write more reliable software - because nobody wants to get paged at 3am for their own bugs. In the podcast, we also touch on: Why deploy time is the foundational feedback loop (15 minutes vs 15 hours changes everything) The controversial "developers on call" stance and why ops people rarely found companies How microservices made everything trace-shaped and killed traditional metrics approaches The "normal engineer" philosophy - building for 4am debugging, not peak performance AI making "code of unknown quality" the new normal Progressive deployment strategies (kibble → dogfood → production) and more 💡 Core Concepts Wide Structured Events : Capturing all request context in one instrumentation event instead of scattered log lines - enables correlation analysis that's impossible with fragmented data. Observability 2.0 : Moving from metrics-as-workhorse to structured-data-as-workhorse, where you instrument once and derive metrics/alerts/dashboards from the same rich dataset. SLO-based Alerting : Replacing symptom alerts (CPU, memory, disk) with customer-impact alerts that measure whether you're meeting promises to users. Progressive Deployment : Gradual rollout through staged environments (kibble → dogfood → production) that builds confidence without requiring 2X infrastructure. Trace-shaped Systems : Architecture pattern recognizing that distributed systems problems are fundamentally about correlating events across time and services, not isolated metrics. 📶 Connect with Charity: LinkedIn Bluesky Personal Blog Company 📶 Connect with Nicolay: LinkedIn X / Twitter Website ⏱️ Important Moments Gateway Drug to Engineering : [01:04] How IRC and bash tab completion sparked Charity's fascination with Unix command line possibilities ADHD and Incident Response : [01:54] Why high-pressure outages brought out her best work - getting "dead calm" when everything's broken Code vs. Production Reality : [02:56] Evolution from focusing on code beauty to understanding performance, behavior, and maintenance over time The Alexander's Horse Principle : [04:49] Auto-deployment as daily practice - if you grow up deploying constantly, it feels natural by the time you scale Production as Source of Truth : [06:32] Why your IDE output doesn't matter if you can't understand your code's intersection with infrastructure and users The Logging Evolution : [08:03] Moving from debugger-style spam logs to fewer, wider structured events oriented around units of work Bubble Up Anomaly Detection : [10:27] How correlating dimensions reveals that failures cluster around specific Android versions, regions, and feature combinations Everything is Trace-Shaped : [12:45] Why microservices complexity is about locating problems in distributed systems, not just identifying them AI as Acceleration of Automation : [15:57] Most AI panic could be replaced with "automation" - it's the same pattern, just faster feedback loops Non-determinism as Genuinely New : [16:51] The one aspect of AI that's actually novel in software systems, requiring new architectural patterns The Cost Crisis : [22:30] How 10-20 observability tools create unsustainable cost multipliers as businesses scale SLO Revolution : [28:40] Deleting 90% of alerts by focusing on customer impact instead of system symptoms Shrinking Feedback Loops : [34:28] Keeping deploy-to-validation under one hour so engineers can connect actions to outcomes Normal Engineer Design : [38:12] Building systems that work for tired humans at 4am, not just heroes during business hours The Instrumentation Habit : [23:15] Always looking at your code in production after deployment to build informed instincts about system behavior Progressive Deployment Strategy : [36:43] Kibble → Dog Food → Production pipeline for gradual confidence building Real Engineering Bar : [49:00] Discussion on what actually makes exceptional vs normal engineers 🛠️ Tools & Tech Mentioned Honeycomb - Observability platform for structured events OpenTelemetry - Vendor-neutral instrumentation framework IRC - Early gateway to computing Parse - Mobile backend where Honeycomb's origin story began 📚 Recommended Resources "In Praise of Normal Engineers" - Charity's blog post "How I Failed" by Tim O'Reilly "Looking at the Crux" by Richard Rumelt "Fluke" - Book about randomness in history "Engineering Management for the Rest of Us" by Sarah Dresner…

How AI Is Built

1
#050 Bringing LLMs to Production: Delete Frameworks, Avoid Finetuning, Ship Faster 1:06:57

לפני 8 weeks1:06:57

1:06:57

Nicolay here, Most AI developers are drowning in frameworks and hype. This conversation is about cutting through the noise and actually getting something into production. Today I have the chance to talk to Paul Iusztin, who's spent 8 years in AI - from writing CUDA kernels in C++ to building modern LLM applications. He currently writes about production AI systems and is building his own AI writing assistant. His philosophy is refreshingly simple: stop overthinking, start building, and let patterns emerge through use. The key insight that stuck with me: "If you don't feel the algorithm - like have a strong intuition about how components should work together - you can't innovate, you just copy paste stuff." This hits hard because so much of current AI development is exactly that - copy-pasting from tutorials without understanding the why. Paul's approach to frameworks is particularly controversial. He uses LangChain and similar tools for quick prototyping - maybe an hour or two to validate an idea - then throws them away completely. "They're low-code tools," he says. "Not good frameworks to build on top of." Instead, he advocates for writing your own database layers and using industrial-grade orchestration tools. Yes, it's more work upfront. But when you need to debug or scale, you'll thank yourself. In the podcast, we also cover: Why fine-tuning is almost always the wrong choice The "just-in-time" learning approach for staying sane in AI Building writing assistants that actually preserve your voice Why robots, not chatbots, are the real endgame 💡 Core Concepts Agentic Patterns: These patterns seem complex but are actually straightforward to implement once you understand the core loop. React : Agents that Reason, Act, and Observe in a loop Reflection : Agents that review and improve their own outputs Fine-tuning vs Base Model + Prompting: Fine-tuning involves taking a pre-trained model and training it further on your specific data. The alternative is using base models with careful prompting and context engineering. Paul's take : "Fine-tuning adds so much complexity... if you add fine-tuning to create a new feature, it's just from one day to one week." RAG: A technique where you retrieve relevant documents/information and include them in the LLM's context to generate better responses. Paul's approach : "In the beginning I also want to avoid RAG and just introduce a more guided research approach. Like I say, hey, these are the resources that I want to use in this article." 📶 Connect with Paul: LinkedIn X / Twitter Newsletter GitHub Book 📶 Connect with Nicolay: LinkedIn X / Twitter Bluesky Website My Agency Aisbach (for ai implementations / strategy) ⏱️ Important Moments From CUDA to LLMs : [02:20] Paul's journey from writing CUDA kernels and 3D object detection to modern AI applications. AI Content Is Natural Evolution : [11:19] Why AI writing tools are like the internet transition for artists - tools change, creativity remains. The Framework Trap : [36:41] "I see them as no code or low code tools... not good frameworks to build on top of." Fine-Tuning Complexity Bomb : [27:41] How fine-tuning turns 1-day features into 1-week experiments. End-to-End First : [22:44] "I don't focus on accuracy, performance, or latency initially. I just want an end-to-end process that works." The Orchestration Solution : [40:04] Why Temporal, D-Boss, and Restate beat LLM-specific orchestrators. Hype Filtering System : [54:06] Paul's approach: read about new tools, wait 2-3 months, only adopt if still relevant. Just-in-Time vs Just-in-Case : [57:50] The crucial difference between learning for potential needs vs immediate application. Robot Vision : [50:29] Why LLMs are just stepping stones to embodied AI and the unsolved challenges ahead. 🛠️ Tools & Tech Mentioned LangGraph (for prototyping only) Temporal (durable execution) DBOS (simpler orchestration) Restate (developer-friendly orchestration) Ray (distributed compute) UV (Python packaging) Prefect (workflow orchestration) 📚 Recommended Resources The Economist Style Guide (for writing) Brandon Sanderson's Writing Approach (worldbuilding first) LangGraph Academy (free, covers agent patterns) Ray Documentation (Paul's next deep dive) 🔮 What's Next Next week, we will take a detour and go into the networking behind voice AI with Russell D’Sa from Livekit. 💬 Join The Conversation Follow How AI Is Built on YouTube , Bluesky , or Spotify . If you have any suggestions for future guests, feel free to leave it in the comments or write me (Nicolay) directly on LinkedIn , X , or Bluesky . Or at nicolay.gerold@gmail.com . I will be opening a Discord soon to get you guys more involved in the episodes! Stay tuned for that. ♻️ I am trying to build the new platform for engineers to share their experience that they have earned after building and deploying stuff into production. Pay it forward by sharing with one engineer who's facing similar challenges. That's the agreement - I deliver practical value, you help grow this resource for everyone. ♻️…

How AI Is Built

1
#050 TAKEAWAYS Bringing LLMs to Production: Delete Frameworks, Avoid Finetuning, Ship Faster 11:00

לפני 8 weeks11:00

11:00

How AI Is Built

1
#049 BAML: The Programming Language That Turns LLMs into Predictable Functions 1:02:38

לפני 9 weeks1:02:38

1:02:38

Nicolay here, I think by now we are done with marveling at the latest benchmark scores of the models. It doesn’t tell us much anymore that the latest generation outscores the previous by a few basis points. If you don’t know how the LLM performs on your task, you are just duct taping LLMs into your systems. If your LLM-powered app can’t survive a malformed emoji, you’re shipping liability, not software. Today, I sat down with Vaibhav (co-founder of Boundary) to dissect BAML —a DSL that treats every LLM call as a typed function. It’s like swapping duct-taped Python scripts for a purpose-built compiler. Vaibhav advocates for building first principle based primitives. One principle stood out: LLMs are just functions; build like that from day 1. Wrap them, test them, and let a human only where it counts. Once you adopt that frame, reliability patterns fall into place: fallback heuristics, model swaps, classifiers—same playbook we already use for flaky APIs. We also cover: Why JSON constraints are the wrong hammer—and how Schema-Aligned Parsing fixes it Whether “durable” should be a first-class keyword (think async/await for crash-safety) Shipping multi-language AI pipelines without forcing a Python microservice Token-bloat surgery, symbol tuning, and the myth of magic prompts How to keep humans sharp when 98 % of agent outputs are already correct 💡 Core Concepts Schema-Aligned Parsing (SAP) Parse first, panic later. The model can handle Markdown, half-baked YAML, or rogue quotes—SAP puts it into your declared type or raises. No silent corruption. Symbol Tuning Labels eat up tokens and often don’t help with your accuracy (in some cases they even hurt). Rename PasswordReset to C7, keep the description human-readable. Durable Execution Durable execution refers to a computing paradigm where program execution state persists despite failures, interruptions, or crashes. It ensures that operations resume exactly where they left off, maintaining progress even when systems go down. Prompt Compression Every extra token is latency, cost, and entropy. Axe filler words until the prompt reads like assembly. If output degrades, you cut too deep—back off one line. 📶 Connect with Vaibhav: LinkedIn X / Twitter BAML 📶 Connect with Nicolay: Newsletter LinkedIn X / Twitter Bluesky Website My Agency Aisbach (for ai implementations / strategy) ⏱️ Important Moments New DSL vs. Python Glue [00:54] Why bolting yet another microservice onto your stack is cowardice; BAML compiles instead of copies. Three-Nines on Flaky Models [04:27] Designing retries, fallbacks, and human overrides when GPT eats dirt 5 % of the time. Native Go SDK & OpenAPI Fatigue [06:32] Killing thousand-line generated clients; typing go get instead. “LLM = Pure Function” Mental Model [15:58] Replace mysticism with f(input) → output; unit-test like any other function. Tool-Calling as a Switch Statement [18:19] Multi-tool orchestration boils down to switch(action) {…}—no cosmic “agent” needed. Sneak Peek—durable Keyword [24:49] Crash-safe workflows without shoving state into S3 and praying. Symbol Tuning Demo [31:35] Swapping verbose labels for C0,C1 slashes token cost and bias in one shot. Inside SAP Coercion Logic [47:31] Int arrays to ints, scalars to lists, bad casts raise—deterministic, no LLM in the loop. Frameworks vs. Primitives Rant [52:32] Why BAML ships primitives and leaves the “batteries” to you—less magic, more control. 🛠️ Tools & Tech Mentioned BAML DSL & Playground Temporal • Prefect • DBOS outlines • Instructor • LangChain 📚 Recommended Resources BAML Docs Schema-Aligned Parsing (SAP) 🔮 What's Next Next week, we will continue going more into getting generative AI into production talking to Paul Iusztin. 💬 Join The Conversation Follow How AI Is Built on YouTube , Bluesky , or Spotify . If you have any suggestions for future guests, feel free to leave it in the comments or write me (Nicolay) directly on LinkedIn , X , or Bluesky . Or at nicolay.gerold@gmail.com . I will be opening a Discord soon to get you guys more involved in the episodes! Stay tuned for that. ♻️ Here's the deal: I'm committed to bringing you detailed, practical insights about AI development and implementation. In return, I have two simple requests: Hit subscribe right now to help me understand what content resonates with you If you found value in this post, share it with one other developer or tech professional who's working with AI That's our agreement - I deliver actionable AI insights, you help grow this. ♻️…

How AI Is Built

1
#049 TAKEAWAYS BAML: The Programming Language That Turns LLMs into Predictable Functions 1:12:34

לפני 9 weeks1:12:34

1:12:34

How AI Is Built

1
#048 TAKEAWAYS Why Your AI Agents Need Permission to Act, Not Just Read 7:06

לפני 10 weeks7:06

7:06

Nicolay here, most AI conversations obsess over capabilities. This one focuses on constraints - the right ones that make AI actually useful rather than just impressive demos. Today I have the chance to talk to Dexter Horthy, who recently put out a long piece called the “12-factor agents”. It’s like the 10 commandments, but for building agents. One of it is “Contact human with tool calls”: the LLM can call humans for high-stakes decisions or “writes”. The key insight is brutally simple. AI can get to 90% accuracy on most tasks - good enough for spam-like activities but disastrous for anything that requires trust. The solution isn't to wait for models to get smarter; it's to add a human approval layer for critical actions. Imagine you are writing to a database or sending an email. Each “write” has to be approved by a human. So you post the email in a Slack channel and in most cases, your sales people will approve. In the 10%, it’s stopped in its tracks and the human can take over. You stop the slop and get good training data in the mean time. Dexter’s company is building exactly this: an approval mechanism that lets AI agents send requests to humans before executing. In the podcast, we also touch on a bunch of other things: MCP and that they are (atm) just a thin client Are we training LLMs toward mediocrity? What infrastructure do we need for human in the loop (e.g. DBOS)? and more 💡 Core Concepts Context Engineering : Crafting the information representation for LLMs - selecting optimal data structures, metadata, and formats to ensure models receive precisely what they need to perform effectively. Token Bloat Prevention : Ruthlessly eliminating irrelevant information from context windows to maintain agent focus during complex tasks, preventing the pattern of repeating failed approaches. Human-in-the-loop Approval Flows : Achieving 99% reliability through a "90% AI + 10% human oversight" framework where agents analyze data and suggest actions but request explicit permission before execution. Rubric Engineering : Systematically evaluating AI outputs through dimension-specific scoring criteria to provide precise feedback and identify exceptional results, helping escape the trap of models converging toward mediocrity. 📶 Connect with Dexter: LinkedIn X / Twitter Company 📶 Connect with Nicolay: LinkedIn X / Twitter Bluesky Website My Agency Aisbach (for ai implementations / strategy) ⏱️ Important Moments MCP Servers as Clients : [03:07] Dexter explains why what many call "MCP servers" actually function more like clients when examining the underlying code. Authentication Challenges : [04:45] The discussion shifts to how authentication should be handled in MCP implementations and whether it belongs in the protocol. Asynchronous Agent Execution : [08:18] Exploring how to handle agents that need to pause for human input without wasting tokens on continuous polling. Token Bloat Prevention : [14:41] Strategies for keeping context windows focused and efficient, moving beyond standard chat formats. Context Engineering : [29:06] The concept that everything in AI agent development ultimately comes down to effective context engineering. Fine-tuning vs. RAG for Writing Style : [20:05] Contrasting personal writing style fine-tuning versus context window examples. Generating Options vs. Deterministic Outputs : [19:44] The unexplored potential of having AI generate diverse creative options for human selection. The "Mediocrity Convergence" Question : [37:11] The philosophical concern that popular LLMs may inevitably trend toward average quality. Data Labeling Interfaces : [35:25] Discussion about the need for better, lower-friction interfaces to collect human feedback on AI outputs. Human-in-the-loop Approval Flows : [42:46] The core approach of HumanLayer, allowing agents to ask permission before taking action. 🛠️ Tools & Tech Mentioned MCP OpenControl DBOS Temporal Cursor 📚 Recommended Resources 12 Factor Agents BAML Docs Rubric Engineering 🔮 What's Next Next week, we will continue going more into getting generative AI into production talking to Vibhav from BAML. 💬 Join The Conversation Follow How AI Is Built on YouTube , Bluesky , or Spotify . If you have any suggestions for future guests, feel free to leave it in the comments or write me (Nicolay) directly on LinkedIn , X , or Bluesky . Or at nicolay.gerold@gmail.com . I will be opening a Discord soon to get you guys more involved in the episodes! Stay tuned for that. ♻️ I am trying to build the new platform for engineers to share their experience that they have earned after building and deploying stuff into production. I am trying to produce the best content possible - informative, actionable, and engaging. I'm asking for two things: hit subscribe now to show me what content you like (so I can do more of it), and if this episode helped you, pay it forward by sharing with one engineer who's facing similar challenges. That's the agreement - I deliver practical value, you help grow this resource for everyone. ♻️…

How AI Is Built

לפני 1 year34:03

34:03

Imagine a world where data bottlenecks, slow data loaders, or memory issues on the VM don't hold back machine learning. Machine learning and AI success depends on the speed you can iterate. LanceDB is here to to enable fast experiments on top of terabytes of unstructured data. It is the database for AI. Dive with us into how LanceDB was built, what went into the decision to use Rust as the main implementation language, the potential of AI on top of LanceDB, and more. "LanceDB is the database for AI...to manage their data, to do a performant billion scale vector search." “We're big believers in the composable data systems vision." "You can insert data into LanceDB using Panda's data frames...to sort of really large 'embed the internet' kind of workflows." "We wanted to create a new generation of data infrastructure that makes their [AI engineers] lives a lot easier." "LanceDB offers up to 1,000 times faster performance than Parquet." Chang She: LinkedIn X (Twitter) LanceDB: X (Twitter) GitHub Web Discord VectorDB Recipes Nicolay Gerold: LinkedIn X (Twitter) Chapters: 00:00 Introduction to LanceDB 02:16 Building LanceDB in Rust 12:10 Optimizing Data Infrastructure 26:20 Surprising Use Cases for LanceDB 32:01 The Future of LanceDB LanceDB, AI, database, Rust, multimodal AI, data infrastructure, embeddings, images, performance, Parquet, machine learning, model database, function registries, agents.…

ברוכים הבאים אל Player FM!

Player FM סורק את האינטרנט עבור פודקאסטים באיכות גבוהה בשבילכם כדי שתהנו מהם כרגע. זה יישום הפודקאסט הטוב ביותר והוא עובד על אנדרואיד, iPhone ואינטרנט. הירשמו לסנכרון מנויים במכשירים שונים.

תקשיבו ל-500+ נושאים

דומה לHow AI Is Built

Mini Mic Pro Wireless Microphone for iPhone, iPad, Android, Lavalier Microphone for Video Recording - 2 Pack iPhone Mic Crystal Clear Recording with USB-C for Podcast, ASMR

As Alive As You Need Me To Be

Bounty Quick Size Paper Towels, White, 8 Family Rolls = 20 Regular Rolls (Packaging May Vary)

פודקאסטים ששווה להאזין

How AI Is Built « » #010 Building Robust AI and Data Systems, Data Architecture, Data Quality, Data Storage

#010 Building Robust AI and Data Systems, Data Architecture, Data Quality, Data Storage

פודקאסטים ששווה להאזין

ברוכים הבאים אל Player FM!

The Let Them Theory: A Life-Changing Tool That Millions of People Can't Stop Talking About

The Let Them Theory: A Life-Changing Tool That Millions of People Can't Stop Talking About

Mighty Patch™ Original patch from Hero Cosmetics – The #1 Hydrocolloid Acne Pimple Patch for Shrinking Zits and Whiteheads in 1 use; Nighttime Spot Stickers for Face and Skin (36 Count)

Crayola Colored Pencils (36ct), Kids Pencil Set, Back to School Essentials, Must Have Classroom Supplies for Kids, Pre-Sharpened Coloring Book Pencils, 3+

The Let Them Theory: A Life-Changing Tool That Millions of People Can't Stop Talking About

דומה לHow AI Is Built

מדריך עזר מהיר

How AI Is Built « »
#010 Building Robust AI and Data Systems, Data Architecture, Data Quality, Data Storage