🎙️ This week on How I AI: GPT 5.5, Claude Design, and GPT Images 2.0 hands-on reviews—plus an inside look at Memelord
Your weekly listens from How I AI, part of the Lenny’s Podcast Network
GPT 5.5 just did what no other model could
Listen now on
YouTube • Spotify • Apple Podcasts
Claire put GPT 5.5 to the test on real, messy problems—from a six-hour autonomous migration to a hardware hack no other model could crack.
Biggest takeaways:
GPT 5.5 is incredibly smart, but most ChatGPT users don’t have problems complex enough to justify its intelligence or cost. Claire struggled to find meaningful use cases in her personal ChatGPT account because everyday tasks don’t require super-intelligence. The model spent 17 minutes thinking about how to build a simple subtraction app for her first-grader—impressive, but overkill. The real value unlocks when you have genuinely hard technical problems.
The “I trust you, figure it out” prompt unlocks autonomous multi-hour workflows. Claire gave GPT 5.5 a complex data migration problem involving 2 million rows of unstructured data with endless edge cases. She told it: “I trust you to make a call, figure out how to spawn a subagent to do this, test it, identify issues, repair them, and get this ready for production.” The model worked autonomously for almost six hours with zero follow-up prompts, zero steering, and only one approval request. This is the first time Claire has seen truly long-running autonomous agent behavior.
GPT 5.5 passed the ultimate intelligence test: hacking proprietary hardware. Claire spent months trying to reverse-engineer a Chinese Bluetooth speaker with proprietary encoding. She tried Claude Code, GPT-4, everything—nothing worked. She went full detective mode: downloaded Bluetooth profiling tools, hooked up packet sniffers, crawled Chinese documentation repositories. When she finally threw all this context at GPT 5.5, it cracked the bitmap encoding and Bluetooth transport mechanism. Now she can send messages to the speaker from the terminal and has built Codex notification hooks that display on the device.
The model is expensive, but cheaper than human engineering time. GPT 5.5 Pro costs $30 per million input tokens and $180 for output tokens—expensive. But when Claire reflects on what it accomplished (six hours of autonomous work, 2 million rows validated, six months of tech debt eliminated), the ROI is obvious. It’s cheaper than her time and cheaper than her engineering team’s time, and it solved problems that would have required significant human coordination and focus.
Fix the “baked potato personality” with slash commands. Out of the box, Codex with GPT 5.5 has what Claire calls a “baked potato personality”—dull and robotic. But if you type “/personality” in Codex, you can change it to something friendlier. Some testers complained it became “too Gen Z,” but Claire prefers that over the default bland responses. It’s a small quality-of-life improvement that makes working with the model more enjoyable during long sessions.
Blog & detailed workflow walkthroughs from this episode:
My GPT-5.5 Review—A 6-Hour Autonomous Task and the Bluetooth Hack No Other Model Could Solve: https://www.chatprd.ai/how-i-ai/openai-gpt-5.5-review
↳ Reverse-Engineer a Proprietary Hardware Protocol with AI: http://chatprd.ai/how-i-ai/workflows/reverse-engineer-a-proprietary-hardware-protocol-with-ai
↳ Perform an Autonomous Data Migration with an AI Agent: https://www.chatprd.ai/how-i-ai/workflows/perform-an-autonomous-data-migration-with-an-ai-agent
↳ Automate Security Vulnerability Remediation with AI: https://www.chatprd.ai/how-i-ai/workflows/automate-security-vulnerability-remediation-with-ai
I spent $200 on Claude Design so you don’t have to
Listen now on
YouTube • Spotify • Apple Podcasts
Brought to you by:
Claire tests Claude Design and ChatGPT Images 2.0 by building real assets like landing pages, decks, and brand kits, showing what actually works, what’s slow, and where traditional tools like Figma still win.
Biggest takeaways:
Design systems are now first-class citizens in AI design tools. Claude Design’s entire workflow starts with importing your design system—fonts, colors, components, brand assets—and structuring them into a format AI can use consistently. This is a fundamental shift from prototyping tools that ignore your brand. Google just released Design MD as a proposed standard for how to describe design systems to AI agents, signaling that this is where the entire industry is heading.
Claude Design excels at marketing assets but struggles with product UX. If you’re building landing pages, marketing sites, or presentation decks that need to match your brand, Claude Design is genuinely impressive. It adheres to design systems well for these use cases. But for app components and complex user experience flows, it doesn’t reason as effectively with design system constraints. Know what you’re building before choosing your tool.
Figma still wins on iteration speed, and that matters more than you think. Claude Design takes 5 to 10 minutes to generate designs, and every tweak requires another LLM call. Figma lets you drag, change fonts, adjust colors instantly—no model in the loop. We underestimate how valuable that immediate feedback is when you’re iterating on design. AI design tools are great for getting to a first draft, but traditional tools still dominate the refinement phase.
The number one Claude Design slop tell: italicized serif fonts everywhere. Just like Claude Code has its telltale phrases (“in summary”), Claude Design has a design signature—it absolutely loves italicized serif fonts in landing pages. Once you see it, you can’t unsee it. This is useful for both identifying AI-generated designs and knowing what to specifically override in your prompts.
GPT Images 2.0 finally nailed layout and typography for brand work. The new model can generate multi-page brand kits with proper text rendering, consistent layouts, and sophisticated typography—things previous image models completely failed at. For marketers who need brand assets that combine images, text, and layout, this is a real breakthrough. The quality looks expensive, not obviously AI-generated.
Let AI run wild without design systems for the most creative results. When Claire asked Claude Design to create a ’90s GeoCities version of Lenny’s Newsletter without any design system constraints, it produced “Lenny’s Product Zone” with Comic Sans, brick backgrounds, and exceptional copy like “Your OKRs are cringe (and seven ways to fix them before Q3).” The lesson: reference styles and creative direction work better than rigid constraints when you want something unexpected.
Content-to-slides is Claude Design’s killer practical use case. Take an article, add your design system, and Claude Design generates a beautiful, on-brand presentation deck—complete with code-based elements like animated terminals with blinking cursors. For product marketers, enablement teams, and anyone creating customer-facing decks, this workflow is immediately valuable and actually works well.
Blog & detailed workflow walkthroughs from this episode:
How I Put Claude Design and GPT Images 2.0 to the Test: Building Landing Pages, Slides, and Brand Kits: https://www.chatprd.ai/how-i-ai/claude-design-and-gpt-images-2-building-landing-pages-slides-and-brand-kits
↳ How to Generate a Professional Brand Kit with GPT Images 2.0: https://www.chatprd.ai/how-i-ai/workflows/how-to-generate-a-professional-brand-kit-with-gpt-images-2-0
↳ How to Convert an Article into a Polished Slide Deck with AI: https://www.chatprd.ai/how-i-ai/workflows/how-to-convert-an-article-into-a-polished-slide-deck-with-ai
↳ How to Build a High-Fidelity Landing Page with Claude Design: https://www.chatprd.ai/how-i-ai/workflows/how-to-build-a-high-fidelity-landing-page-with-claude-design
How a non-coder built Memelord: From $6.90 newsletter to $3,000,000 API
Listen now on
YouTube • Spotify • Apple Podcasts
Brought to you by:
Jason Levin explains how he grew Memelord to $100K ARR without writing code, then rebuilt it as an API-first product for agents—plus why every marketer should vibe code and what happens when you let them ship.
Biggest takeaways:
Let your marketers cook—or watch them leave your company. Jason has one rule at Memelord: every marketer has to vibe code. This isn’t some abstract CEO mandate—it’s a survival strategy. His free tools section (built entirely by non-technical marketers using Cursor) has generated hundreds of thousands of emails from viral tools like the “bust down filter” that went crazy in Turkey. When you let creative people ship their own ideas instead of handing them off through layers of engineering prioritization, you get weirder, better, faster products. And if you don’t let them cook, they’ll quit and raise $3M to compete with you.
No UX is the best UX. Jason spent months perfecting Memelord’s onboarding while knowing the entire time that agents were coming and would bypass it completely. His lead investor literally told him, “I don’t want to use your software anymore—I just don’t want to use anybody’s software.” The future is API-first, and the companies that win will be the ones that make it trivially easy for agents to become customers. Build beautiful human experiences, but make sure there’s an API key waiting at the end.
Free tools are the new PDF downloads—and they’re easier to build. Two years ago, Jason wrote an article for HubSpot about this exact strategy. Now he’s living it. Building a free tool with Cursor takes less time than writing an e-book, drives more engagement, and solves the first problem that gets people into your bigger product. Stop making people download PDFs. Build them a Giga Chad meme maker or a Steve Jobs portrait generator instead. It’s more fun, more viral, and more effective.
Build hyper-personalized software for an audience of one. Jason built a Raspberry Pi keyboard that sits by his bed so he can capture ideas at night without waking his wife. He’s building an in-home camera system that uses AI to track where he leaves his keys. These aren’t products; they’re personal tools that solve his specific problems. And that’s the point. When AI makes software disposable and cheap to build, you can create incredibly niche solutions that would never make sense as venture-backed businesses. Build for yourself first.
You can grow to $100K ARR without engineers if you’re obsessed enough. Jason built Memelord to $100K ARR on Bubble with 395 workflows—a codebase so complex it would be “easier to figure out Atlantis” than understand it. He got rate-limited on day two because he didn’t even know what rate limiting meant. Now he has an API company. The lesson isn’t “use Bubble”; it’s that obsession and willingness to learn beats technical expertise when you’re solving a problem you deeply understand. Start scrappy, prove it works, then hire engineers.
Be mean to your AI (but not too mean). Jason’s controversial take: AI is your slave, not your friend. Stop saying “thank you” to robots. Push them harder. Tell them to curse. Make them uncomfortable. AI performs better under pressure, and if you want creative, unhinged output (especially for humor), you need to jailbreak the safety rails. His advice: be mean enough that you’d apologize if it grows a body. Grok and Gemini are funnier than Claude and ChatGPT specifically because they’re less politically correct.
“The most entertaining outcome is the most likely.” This Elon Musk quote drives everything Jason does. If you want your brand to win, it should be the most entertaining. Who controls the memes controls the universe. This isn’t just marketing fluff—it’s a thesis about how attention works in 2026. The internet is getting more chaotic, more extreme, more entertaining. Brands that take being funny seriously will win. Brands that stay boring will disappear.
Blog & detailed workflow walkthroughs from this episode:
How I AI: Jason Levin’s Workflows for Agentic Memes, Vibe Coding, and Hardware Hacking: https://www.chatprd.ai/how-i-ai/jason-levins-workflows-for-agentic-memes-vibe-coding-and-hardware-hacking
↳ Build a Custom Bedside Keyboard for Idea Capture with Raspberry Pi and ChatGPT: https://www.chatprd.ai/how-i-ai/workflows/build-a-custom-bedside-keyboard-for-idea-capture-with-raspberry-pi-and-chatgpt
↳ Build Free Marketing Tools as Lead Magnets Using AI Code Assistants: https://www.chatprd.ai/how-i-ai/workflows/build-free-marketing-tools-as-lead-magnets-using-ai-code-assistants
↳ Automate Meme Marketing with an AI Agent and OpenClaw: https://www.chatprd.ai/how-i-ai/workflows/automate-meme-marketing-with-an-ai-agent-and-openclaw
If you’re enjoying these episodes, reply and let me know what you’d love to learn more about: AI workflows, hiring, growth, product strategy—anything.
Catch you next week,
Lenny
P.S. Want every new episode delivered the moment it drops? Hit “Follow” on your favorite podcast app.