Go offline with the Player FM app!
#243 - The 70% Problem: When AI Coding Falls Short
Manage episode 485595811 series 3399111
Send a text and I may answer it on next episode (I cannot reply from this service 😢)
What happens when software engineers rely too heavily on AI-assisted coding tools? Brian and Zubin (an ex-Google engineer) dive deep into what they call "The 70% Problem" – the phenomenon where AI coding tools excel at initial scaffolding but falter when tackling the crucial final 30% of engineering work.
Drawing from Addy Osmani's insightful article, these experienced developers share their firsthand experiences with tools like Cursor, ChatGPT, and GitHub Copilot. They explore how AI-assisted coding creates a dangerous illusion of competence while potentially masking fundamental knowledge gaps. As Zubin aptly puts it, giving powerful AI coding tools to inexperienced developers is like "giving a Formula One car to someone who's only driven on city streets."
Visit parsity.io to learn how Brian and Zubin are training the next generation of engineers to excel in this new paradigm.
Shameless Plugs
🧠 (NEW) Parsity's The Inner Circle Program - a highly customized roadmap to take you from 0 to hired. For career changers who want to pivot into software.
💼 Zubin's LinkedIn (ex-lawyer, former Google, Brian-look-a-like)
👂🏻Easier Said Than Done Podcast
Already a developer? Check out 👉 Not Another Course
Serious about joining Parsity? Schedule a call with me ☎️
Chapters
1. Introducing the 70% Problem (00:00:00)
2. AI Coding: Productivity vs Quality (00:05:11)
3. The Hidden Cost of Vibe Coding (00:08:41)
4. Why Learning Fundamentals Still Matters (00:17:50)
5. Engineering Judgment Can't Be Delegated (00:26:25)
6. Best Practices for AI as a Team Member (00:29:40)
248 episodes
Manage episode 485595811 series 3399111
Send a text and I may answer it on next episode (I cannot reply from this service 😢)
What happens when software engineers rely too heavily on AI-assisted coding tools? Brian and Zubin (an ex-Google engineer) dive deep into what they call "The 70% Problem" – the phenomenon where AI coding tools excel at initial scaffolding but falter when tackling the crucial final 30% of engineering work.
Drawing from Addy Osmani's insightful article, these experienced developers share their firsthand experiences with tools like Cursor, ChatGPT, and GitHub Copilot. They explore how AI-assisted coding creates a dangerous illusion of competence while potentially masking fundamental knowledge gaps. As Zubin aptly puts it, giving powerful AI coding tools to inexperienced developers is like "giving a Formula One car to someone who's only driven on city streets."
Visit parsity.io to learn how Brian and Zubin are training the next generation of engineers to excel in this new paradigm.
Shameless Plugs
🧠 (NEW) Parsity's The Inner Circle Program - a highly customized roadmap to take you from 0 to hired. For career changers who want to pivot into software.
💼 Zubin's LinkedIn (ex-lawyer, former Google, Brian-look-a-like)
👂🏻Easier Said Than Done Podcast
Already a developer? Check out 👉 Not Another Course
Serious about joining Parsity? Schedule a call with me ☎️
Chapters
1. Introducing the 70% Problem (00:00:00)
2. AI Coding: Productivity vs Quality (00:05:11)
3. The Hidden Cost of Vibe Coding (00:08:41)
4. Why Learning Fundamentals Still Matters (00:17:50)
5. Engineering Judgment Can't Be Delegated (00:26:25)
6. Best Practices for AI as a Team Member (00:29:40)
248 episodes
All episodes
×Welcome to Player FM!
Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.