Insight certainty 4/5 debate potential 1/5

Kilpatrick: Prompting models for 5 extra features solves vibe coding block

Logan Kilpatrick · Google's Gemini 3.0: The Most Powerful LLM Ever · Nov 18, 2025 · at 21:15

Google DeepMind's Logan Kilpatrick describes his iterative prototyping heuristic when building applications with Gemini in Google AI Studio.

0:00 / 0:28exact quote · 28.7s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“And I, my routinely use this sort of prompt, which I have here, which is just like add in five additional features. And the model sort of takes in all this context and all these ideas that I wouldn't have thought of. And like, even if they're crappy ideas, I can always just remove those features. But like the one feature that shows up here, that's like actually really great. It, it's just like, it feels like that magic moment. So I feel like that loop of just like add five additional features, let the model figure out what they are and then play around with them works really, really well.”

quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →

More from Logan Kilpatrick

Assertion Partly supported
Kilpatrick: Gemini 3.0 Pro API undercuts GPT-5.1 Pro and Claude 4.5
“The actual model is two dollars per million input tokens and 12 dollars per million output tokens. So it's priced below some of those sort of comparable competitive models like GBT, 5.1 pro as an example, and Claude 4.5.”
Logan Kilpatrick Nov 18, 2025 ▶ 19:53 Google's Gemini 3.0: The Most Powerful LLM Ever
Insight
Direct AI creation preserves story fidelity better than human intermediary layers
“What happens when you, as the person who like has a story to tell or like some idea, you have to like put it through this translate, this translation layer, especially when the translation layer is sometimes like a, you know, a bunch of people or something lik…”
Logan Kilpatrick Aug 27, 2025 ▶ 12:32 I got a private lesson on Google's NEW Nano Banana AI Model
Assertion Contradicted
Image quality does not degrade across multi-turn AI conversational edits
“The model doesn't like the image quality doesn't get worse as you like do a multi-turn edit. So like you don't need to get everything right on the first edit.”
Logan Kilpatrick Aug 27, 2025 ▶ 20:30 I got a private lesson on Google's NEW Nano Banana AI Model
Prediction Not checkable as stated
Kilpatrick: Real-time multimodal models will become co-present pair programmers
“I think the future that we're going to see with the multimodal live API is really the ability for the model to or just like generally for models to be co-present in the experiences that you are. And like, you could imagine your IDE is the best experience of th…”
Logan Kilpatrick Feb 15, 2025 ▶ 23:11 Google AI studio replaces your AI tech stack (full demo)
Assertion Not checkable as stated
Kilpatrick: Users can vibe-code real-time games with Gemini 3 Pro
“And I think with Gemini Three Pro, you can just, Vibe code games in real time, which is really, really awesome.”
Logan Kilpatrick Nov 18, 2025 ▶ 3:30 Google's Gemini 3.0: The Most Powerful LLM Ever
Insight
Kilpatrick: Generating games is a proxy for an LLM's overall sophistication
“Games are just a proxy for like the model's overall capability. So like, Hey, maybe you're like, I don't actually care about building games. I think as you see some of these examples, it like speaks to the level of sophistication that the model has an understa…”
Logan Kilpatrick Nov 18, 2025 ▶ 4:35 Google's Gemini 3.0: The Most Powerful LLM Ever
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 300 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.