The Programming Podcast

We are breaking down the massive AI news surrounding the recent security breach. This episode discusses the unprecedented anthropic leak, which exposed the claude source code and led to a significant claude code leak, impacting half a million lines of code. We explore the implications of this event and what it means for cyber security in the AI world.

💡 Sponsor: Huge shoutout to Auth0!
Secure AI agents, humans, and whatever comes next
https://auth0.com/

✅ If you made it to the end, comment: “Claude Code Undercover” so we know who is a real one!

https://www.commityourcode.com/
Come to CYC!

Get The Developers Guide To AI here!
http://developersguide.ai/

SITE https://www.programmingpodcast.com/

Stay in Touch:
📧 Have questions for the show? Or are you a business that wants to talk business?
Email us at [email protected]!

Danny Thompson
https://x.com/DThompsonDev
www.DThompsonDev.com

Leon Noel
https://x.com/leonnoel
https://100devs.org/

📧 Have questions for the show? Or are you a business that wants to talk business?
Email us at [email protected]!

Subscribe if you want honest, no-hype conversations about where software development is heading in 2026.

Chapters
00:00 - Intro: The Largest AI Leak in History
01:47 - By the Numbers: Secret Variables, Commands & Build Flags
03:17 - Coordinator Mode & The Sub-Agent Hierarchy
06:56 - UDS Inbox & Auto Dream: The Future of AI Memory
10:24 - Auth0
10:51 - Uncovering Hidden Slash Commands (/dream, /bug_hunter)
13:41 - Exploring Claude's New Voice Mode & Dictation Tools
16:26 - "Undercover Mode": Ghostwriting Open Source Commits
18:27 - The Not-So-Fun Leaks: 6x Fast Mode Markups & HIPAA Limits
23:34 - Breaking Down Claude's Step-by-Step Query Loop Architecture
26:59 - OpenAI's Massive $150 Billion Valuation Announcement
28:03 - Ask Danny: The Ultimate Post-Coffee Chat Follow-Up Strategy
35:27 - Outro & Wrap-Up

With AI tools writing 90% of the code out there and "vibe coding" taking over our timelines, is learning the fundamentals of software engineering a waste of time? Leon and I sit down to finally answer the question we get asked every single day. We break down the truth about the "Agentic Era," why skipping the basics will break your apps in production, and how skills-based hiring is fundamentally changing what employers look for. If you are learning to code right now, or trying to land your next role, this is the exact roadmap you need to become the "AI-Augmented Engineer" that companies are desperately looking for.

💡 Sponsor: Level Up Financial Planning
Changing careers or increasing your income? Get financial clarity with Level Up Financial Planning—helping early and mid-career tech professionals secure their financial future. Visit LevelUpFinancialPlanning.com for a free consultation!
https://www.levelupfinancialplanning.com/

I wrote a book on AI! Check it out here http://developersguide.ai/

🔥 MAJOR ANNOUNCEMENT:
Commit Your Code 2026 is officially happening! Join us September 3rd & 4th in Plano, Texas. $40 tickets, 100% goes to charity. Come for the JavaScript, AI, and startup tracks—stay for the 90-minute hands-on workshops.

SITE https://www.programmingpodcast.com/

Stay in Touch:
📧 Have questions for the show? Or are you a business that wants to talk business?
Email us at [email protected]!

Danny Thompson
https://x.com/DThompsonDev
www.DThompsonDev.com

Leon Noel
https://x.com/leonnoel
https://100devs.org/

📧 Have questions for the show? Or are you a business that wants to talk business?
Email us at [email protected]!

Video Chapters
0:00 - The Big Question: Do You Still Need to Learn to Code?
1:00 - HUGE Announcement: Commit Your Code 2026 is Back!
3:35 - The Thesis: Why AI Will Make You Ship "Bad Stuff" Faster
6:05 - Is AI Really Writing 90% of the World's Code?
8:13 - What Happened When a Coding Bootcamp Allowed AI
9:22 - Sponsor Break: Level Up Financial Planning
10:22 - The "New Edge": Why 71% of Leaders Prefer AI-Augmented Juniors
12:10 - Vibe Coding, AI "Slop," and Content Generation
16:22 - Vercel’s CEO on Why Fundamentals Matter More Than Ever
19:34 - NACE Data: Skills-Based Hiring is Up 70% (GPA is Dead)
21:19 - The Exact 6-Month Roadmap to Become an AI-Augmented Dev
23:42 - Stop Guessing: How to Find the Tech Stack in Demand in Your City
27:10 - The Ultimate Trap: Using AI Too Early in Your Learning Journey
30:28 - What Recruiters Actually Want (Hint: It’s Not Syntax)
32:33 - Real Resume Review: Why Your Bullet Points Have No Strategy
36:01 - Q&A: Should You Accept a Lowball Job Offer?
38:40 - Why Cold Applying is Failing You (Teaser for Next Episode)

LeetCode is dead… or is it?

HackerRank dropped a bold take that set the internet on fire: “LeetCode is dead,” because devs do not write code line-by-line anymore. We orchestrate AI, debug its output, and catch failures in real time. So if the job changed, should interviews finally change too?

💡 Sponsor: Huge shoutout to Auth0!
Secure AI agents, humans, and whatever comes next
https://auth0.com/

In this episode, Danny Thompson and Leon Noel break down what HackerRank is really saying, why LeetCode traffic is still exploding, and what the “new interview” is starting to test: fundamentals plus AI fluency.

We talk about the lag you should expect from big companies, how to think about DSA strategically (especially if you are not targeting FAANG), and what modern AI competency looks like in practice. Prompting is not typing faster. It is context engineering. Question, not command.

Then we tackle a listener question: “I’m a junior dev and my job doesn’t use any tools that make me competitive. How do I level up in AI?” The answer is direct: growth is not guaranteed at work, so you have to build it yourself. Tools, models, workflows, and habits that keep you ahead.

If you are prepping for interviews in 2026, this is your roadmap for what to keep, what to drop, and what to add.

✅ If you made it to the end, comment: “Documentation Traffic.” so we know who is a real one!

SITE https://www.programmingpodcast.com/

Stay in Touch:
📧 Have questions for the show? Or are you a business that wants to talk business?
Email us at [email protected]!

Danny Thompson
https://x.com/DThompsonDev
/ dthompsondev
www.DThompsonDev.com

Leon Noel
https://x.com/leonnoel
/ leonnoel
https://100devs.org/

📧 Have questions for the show? Or are you a business that wants to talk business?
Email us at [email protected]!

Subscribe if you want honest, no-hype conversations about where software development is heading in 2026.

Chapters (YouTube)

0:00 HackerRank says “LeetCode is dead”
1:15 Welcome + intros (Danny Thompson, Leon Noel)
1:55 Danny’s Atlassian update: Forge, Marketplace reach, and what’s coming
3:26 Why this HackerRank post matters (they have the hiring data)
4:34 Interviews must evolve: testing AI usage, not just algorithms
5:14 HackerRank’s AI IDE idea: evaluating prompts and process
6:34 “LeetCode isn’t dead” counterpoint: traffic is climbing again
7:24 Why adoption lags: companies will keep old interviews for years
9:12 Practical strategy: DSA still opens doors, but it’s not the only door
10:59 Sponsor: Auth0 (identity for AI agents)
11:46 FAANG vs non-FAANG prep: how deep you actually need to go
13:03 Some companies “think they’re FAANG” and what that signals
13:52 Interview mindset shift: show everything, don’t hope they notice
15:57 The new skill set: fundamentals + AI fluency
16:31 Why most people think AI “sucks” and how to fix it
18:05 The core: context before commands (index first, act second)
20:35 Vibe coding vs AI engineering: the difference is the setup
21:45 Transactional prompting trap + the “drop shadow” example
23:09 Use AI like a blunt senior engineer to challenge your assumptions
25:00 “Question, not command” as a simple upgrade
25:36 The new layer: tools, agents, MCPs, workflows, AI-augmented engineering
27:42 Internal knowledge tools (Rovo) and why focused context wins
29:25 Ask Danny & Leon: “My job doesn’t use AI tools. How do I stay competitive?”
29:57 “Learning doesn’t happen on the job” and how to level up outside work
31:10 Try models, tools, and agentic workflows (Cursor, etc.)
32:06 Bring the value back to work: prove productivity, then ask for adoption
33:00 Your circle changes your ceiling (community as a force multiplier)
35:09 A job dictates pay, you dictate worth
36:19 Closing: keep learning, keep growing, see you next episode

For the last 18 months, we’ve been hearing that “AI is Magic.” But what happens when you connect that “magic” to your production database, your billing APIs, and your enterprise systems? It becomes a financial ticking time bomb.

In this episode of The Programming Podcast, Leon and I sit down with Monica Bajaj, VP of Engineering at Okta. We are tearing down the "God Mode" tutorials you see on YouTube and talking about the terrifying engineering reality of Agentic AI.

We break down the "Infinite Loop from Hell," why you need to start treating your AI like a Junior Developer with a corporate credit card, and how to actually secure your architecture before your agent bankrupts your company at 2:00 AM. If you are building with AI, deploying MCP servers, or just trying to figure out this new frontier—you cannot afford to miss this one.

In this episode, we cover:

- The "Financial Blast Radius" of uncontrolled AI actions
- The 3 P's Framework: Purpose, Privilege, and Protection
- Why standard Rate Limiting isn't enough (and why you need MCP Gateways)
- Token Vaults, the "5-Minute Pulse Check," and Dynamic Zero Trust
- Overcoming Imposter Syndrome when the tech world resets

Make sure to hit that like button, subscribe, and let us know in the comments: Are you giving your AI agents "God Mode"?

Follow Monica Bajaj: https://www.linkedin.com/in/mobajaj/

Chapter Timestamps:
0:00 - The Wake-Up Call: Why AI is Dangerous, Not Just Magic
0:53 - Welcome Monica Bajaj (VP of Engineering, Okta)
3:08 - The "Probabilistic Runtime" & Identity Blind Spots
5:02 - Accidental Agent Sprawl & Draining Cloud Credits
6:50 - The "Infinite Loop From Hell" (Bankrupting Your Company)
9:24 - Financial Blast Radius vs. Text Hallucinations
12:17 - The Danger of Giving AI "God Mode"
14:26 - The 3 P's Framework: Purpose, Privilege, & Protection
16:44 - The Biggest Anti-Pattern in Early Agent Builds
18:23 - Purpose: Why Agents Need a "Job Description"
20:25 - Privilege: The "Junior Dev with a Credit Card" Metaphor
24:48 - Protection: Why Rate Limiting Isn't Enough (MCP Gateways)
27:29 - Token Vaults & The 5-Minute Pulse Check
30:32 - The SHIELD Acronym & Dynamic Zero Trust
33:18 - Buy vs. Build: Identity in the Agentic Era
40:03 - The 2 AM Test (If You Can't Stop It, You Can't Ship It)
44:24 - Q&A: Overcoming AI Imposter Syndrome
47:09 - Danny's Mic Drop: Why We Are All Imposters Right Now

In this episode, Danny and Leon break down a massive 48 hours in AI. With the surprise drop of Anthropic Opus 4.6 and OpenAI’s Codex 5.3, the landscape for software engineers has shifted again. We dive deep into what a 1-million-token context window actually means for your workflow, the rise of Agent Teams, and why "vibe coding" recently led to a massive security blunder in the dev community. We also answer a listener question about whether custom code or off-the-shelf builders like Shopify are the right choice for small business clients.

📑 Chapters
0:00 – Intro: The Drake vs. Kendrick of AI Drops

1:20 – Opus 4.6 Metrics & Terminal Bench 2.0

3:02 – The 1-Million-Token Window: Game Changer or Overkill?

4:36 – How Large Context Affects Codebase Scanning

5:45 – Adaptive vs. Extended Thinking: Effort Parameters Explained

7:50 – The Gemini Ratchet: How Google Set the Standard for Context

9:15 – Playwright & MCP: Unlocking Visual Testing with Massive Windows

10:55 – Understanding Context Rot & Reduction in Long Chats

13:30 – Does a Million Tokens Kill RAG? (Retrieval-Augmented Generation)

14:35 – Orchestration Layers: Sub-Agents vs. Agent Teams

17:23 – Cost Analysis: Comparing Sonnet 4.5 vs. Opus 4.6 Pricing

20:00 – Anthropic’s Response to Developer Complaints (The "Think Harder" Meme)

22:20 – Skill Frameworks & Code Standards Files

24:45 – The "Feel" of the Model: Speed vs. Risk-Taking in Logic

27:00 – Current Dev Workflows: When to switch to Codex 5.3

30:50 – Prompt Engineering in the Thinking Model Era

32:45 – Sam Altman’s "Bar" & The Reality of Benchmarks

36:15 – Is Coding Dead? Addressing the Hype Cycle and Management Fears

37:55 – The "Maltbot" Security Blunder: Why Humans Must Stay in the Loop

42:15 – AI in WebDev vs. Embedded Systems & Cloud

45:55 – Q&A: Website Builders (Shopify/Wix) vs. Custom Code for Clients

50:50 – Final Thoughts: Selling Your Time and Knowledge, Not Just Syntax