![[The AI Show Episode 146]: Rise of “AI-First” Companies, AI Job Disruption, GPT-4o Update Gets Rolled Back, How Big Consulting Firms Use AI, and Meta AI App](https://www.marketingaiinstitute.com/hubfs/ep%20146%20cover.png)
.jpg?width=1920&height=1920&fit=bounds&quality=70&format=jpg&auto=webp#)
.jpg?#)
_Alexey_Kotelnikov_Alamy.jpg?width=1280&auto=webp&quality=80&disable=upscale#)
_Brian_Jackson_Alamy.jpg?width=1280&auto=webp&quality=80&disable=upscale#)
_Steven_Jones_Alamy.jpg?width=1280&auto=webp&quality=80&disable=upscale#)
 Stolen 884,000 Credit Card Details on 13 Million Clicks from Users Worldwide.webp?#)
![Roku clarifies how ‘Pause Ads’ work amid issues with some HDR content [U]](https://i0.wp.com/9to5google.com/wp-content/uploads/sites/4/2025/05/roku-pause-ad-1.jpg?resize=1200%2C628&quality=82&strip=all&ssl=1)
![Look at this Chrome Dino figure and its adorable tiny boombox [Gallery]](https://i0.wp.com/9to5google.com/wp-content/uploads/sites/4/2025/05/chrome-dino-youtube-boombox-1.jpg?resize=1200%2C628&quality=82&strip=all&ssl=1)
![Apple Seeds visionOS 2.5 RC to Developers [Download]](https://www.iclarified.com/images/news/97240/97240/97240-640.jpg)
![Apple Seeds tvOS 18.5 RC to Developers [Download]](https://www.iclarified.com/images/news/97243/97243/97243-640.jpg)
![Apple Releases macOS Sequoia 15.5 RC to Developers [Download]](https://www.iclarified.com/images/news/97245/97245/97245-640.jpg)
“It Looked Right…” Famous Last Words Without Tests
TL;DR: LLMs are great, but they’re not your safety net. Please, for the love of all things holy, test your code. We’re in the golden age of vibe coding. LLMs scaffold our code, fix our syntax, and fill in the blanks. We’re thinking more about architecture and less about syntax—and that’s great. But in all this abstraction, we sometimes skip something essential: testing. LLMs Sound Right — Until They’re Not AI doesn’t run your code. It doesn't know if that method exists, if that call will throw an error, or if that edge case breaks everything. It’s bluffing with confidence. You can’t vibe your way through correctness. You need tests to know your code behaves the way you think it does. Why Testing Still Matters
TL;DR:
LLMs are great, but they’re not your safety net. Please, for the love of all things holy, test your code.
We’re in the golden age of vibe coding. LLMs scaffold our code, fix our syntax, and fill in the blanks. We’re thinking more about architecture and less about syntax—and that’s great.
But in all this abstraction, we sometimes skip something essential: testing.
LLMs Sound Right — Until They’re Not
AI doesn’t run your code. It doesn't know if that method exists, if that call will throw an error, or if that edge case breaks everything. It’s bluffing with confidence.
You can’t vibe your way through correctness. You need tests to know your code behaves the way you think it does.
