From Streaker Apps to AI Safety Loopholes: What CTOs Need to Know
How Many CTOs16 Sep 2025

From Streaker Apps to AI Safety Loopholes: What CTOs Need to Know

In this episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub break down the quirky and serious sides of today's AI. They cover vibe coding, smart glasses, debugging with ChatGPT, and the big question of whether AI gets weaker without human content, offering practical takeaways for CTOs.

They tackle topics like:

  • Vibe coding during a meeting: Scott builds a full React Native "streaker" app using Augment Code and Gemini — without touching a line of code.

  • Smart glasses and privacy: What happens when you realize your acquaintance might be recording you in a casual setting?

  • AI safety filters: How clever prompting can slip past restrictions, raising tough questions about the limits of AI guardrails.

  • JSON prompting experiments: Could structured prompts outperform natural language instructions?

  • Debugging with AI: Brad drops raw errors straight into ChatGPT and gets back surprisingly accurate, context-aware fixes.

  • The ouroboros problem: If AI increasingly trains on AI-generated text instead of human-created content, will models eventually get dumber?

From practical dev hacks to big-picture concerns, this episode shines a light on the curious intersection of AI technology and human behavior.

  • 00:00 Introduction: A Fun AI Chat Experiment
  • 00:29 Podcast Opening and AI Update
  • 01:15 Hacker News Game: Counting AI Articles
  • 02:52 Smart Glasses and Privacy Concerns
  • 06:06 Vibe Coding: Creating an App During a Meeting
  • 11:12 AI Image Generation: Navigating Content Restrictions
  • 13:43 AI Safety Challenges and JSON Prompting
  • 17:54 Introduction to JSON Prompting
  • 18:03 Examples of Structured Prompts
  • 19:28 Real-World Application of AI Prompts
  • 21:15 Understanding AI's Context Awareness
  • 21:38 Exploring AI's Knowledge Sources
  • 25:17 Personal Experiences with AI
  • 32:55 The Future of AI-Generated Content
  • 39:06 Concluding Thoughts and Reflections

Resources:

#TechPodcast #EngineeringPodcast #DevTalks #PodcastForDevs #HowManyCtos #Podcast #Ctos #CtoPodcast #Technology #Engineering #SoftwareDevelopment #TechLeadership #EngineeringLeadership #AIUpdate #AIDevelopment #AIsafety #JSONprompting #SmartGlasses #GenerativeAI #DebuggingWithAI #VibeCoding

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(85)

The Hardware/Software Blend: Visionary Innovations in Health Tech with Eyebot's Jack Moldave

The Hardware/Software Blend: Visionary Innovations in Health Tech with Eyebot's Jack Moldave

In this episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub interview Jack Moldave of Eyebot, a company he co-founded nearly six years ago to make getting glasses a...

1 Sep 52min

Fast, On Time, or Fully Utilized? Choosing What to Optimize in Engineering Delivery

Fast, On Time, or Fully Utilized? Choosing What to Optimize in Engineering Delivery

In this episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub discuss a leadership conversation where three senior stakeholders wanted different outcomes from enginee...

25 Aug 16min

The Pace of Innovation: Systems Thinking for Faster Engineering

The Pace of Innovation: Systems Thinking for Faster Engineering

In this episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub open with travel and sports talk, including World Cup rules, then pivot to Scott's change-management tra...

18 Aug 56min

Method to the Madness: A CTO Framework for Systemic AI Adoption

Method to the Madness: A CTO Framework for Systemic AI Adoption

In this episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub discuss how CTOs must frame narratives that help teams organize around ideas, inspired by how Scott expl...

11 Aug 45min

There's A Pattern To Follow: An Interview with Robert "Uncle Bob" Martin

There's A Pattern To Follow: An Interview with Robert "Uncle Bob" Martin

In this episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub are honored to interview Robert "Uncle Bob" Martin, who recounts his 60+ year programming journey from a...

4 Aug 1h 1min

Is Uncle Bob Right? Reading Code vs. Architecting the Future

Is Uncle Bob Right? Reading Code vs. Architecting the Future

In this episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub discuss how Robert "Uncle Bob" Martin—author of Clean Code and Agile Manifesto signer—sparked online con...

28 Jul 43min

Token Maxxing and Local Inference: Navigating the Shift in AI Usage for Developers

Token Maxxing and Local Inference: Navigating the Shift in AI Usage for Developers

In this episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub discuss token spending and the "token maxing" backlash, sparked by a GitHub Copilot budget issue and bro...

21 Jul 1h

This Has Always Been A Problem: Slot Machine Devs and Growing Junior Engineers in the Age of AI

This Has Always Been A Problem: Slot Machine Devs and Growing Junior Engineers in the Age of AI

In this episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub discuss how managing armies of coding agents can be physically draining, likening it to context switchin...

14 Jul 56min

Populært innen Business og økonomi

stopp-verden
dine-penger-pengeradet
e24-podden
rss-penger-polser-og-politikk
lydartikler-fra-aftenposten
rss-borsmorgen-okonominyhetene
rss-skravla-gar
finansredaksjonen
rss-pa-konto
pengepodden-2
tid-er-penger-en-podcast-med-peter-warren
pengesnakk
lederpodden
livet-pa-veien-med-jan-erik-larssen
rss-orjasater
stormkast-med-valebrokk-stordalen
morgenkaffen-med-finansavisen
utbytte
liberal-halvtime
rss-markedspuls-2