Monica Cheng

@edgardesigns good Friday！

Happy good friday tech bros🙏

@elonmusk Grok is amazing really

Grok Imagine

@elonmusk grok is really good

Video Killed the Radio Star

@antonosika @iamwill love to see real user feedback

Hung out with a Lovable super-user, who also happens to be a big creator of culture for my generation. It was great to catch up with you, @iamwill.

@Martinoleary @steipete So true

@MeredithCheng22 @steipete this week it's been really bad

I keep hitting quota limits from GitHub's API. This hasn't been designed with agents in mind.

@lennysan @simonw November 2025 feel like last century, the ai make time flys

My biggest takeaways from @simonw: 1. November 2025 was an inflection point for AI coding. GPT 5.1 and Claude Opus 4.5 crossed a threshold where coding agents went from “mostly works” to “almost always does what you want it to do.” Software engineers who tinkered over the holidays realized the technology had become genuinely reliable. 2. Mid-career engineers are the most vulnerable—not juniors, not seniors. AI amplifies experienced engineers by letting them leverage decades of pattern recognition. It also dramatically helps new engineers onboard. Cloudflare and Shopify each hired a thousand interns because AI cut ramp-up time from a month to a week. But mid-career engineers who haven’t accumulated deep expertise and have already captured the beginner boost are in the most precarious position. 3. AI exhaustion is real and underestimated. Simon runs four coding agents in parallel and is mentally wiped out by 11 a.m. He’s getting more time back, but his brain is exhausted from the intensity of directing multiple autonomous workers. Some engineers are losing sleep to keep agents running. This may just be a novelty issue, but the underlying dynamic—that managing AI amplifies cognitive load even as it reduces labor—is a real tension. Good companies will manage expectations rather than expecting 5x output indefinitely. 4. Code is cheap now. This simple idea has profound implications. The thing that used to take most of the time—writing code—now takes the least. The bottleneck has shifted to everything else: deciding what to build, proving ideas work, getting user feedback. Since prototyping is nearly free, Simon often builds three versions of every feature when he’s getting started. 5. The “dark factory” is the most radical experiment in AI-assisted development happening right now. A company called StrongDM established a policy: nobody writes code, nobody reads code. Instead, they run a swarm of AI-simulated end users 24/7—thousands of fake employees making requests like “give me access to Jira”—at $10,000 a day in token costs. They even had coding agents build simulated versions of Slack, Jira, and Okta from API documentation so they could test without rate limits. 6. "Red/green TDD" is the single highest-leverage agentic engineering pattern. Having coding agents write tests first, watch them fail, then write the implementation, then watch them pass produces materially better results. The five-word prompt “use red/green TDD” encodes this entire workflow because the agents recognize the jargon. 7. “Hoarding things you know how to do” is one of Simon's other favorite agentic engineering patterns. Simon maintains a GitHub repo of 193 small HTML/JavaScript tools and a separate research repo of coding-agent experiments. Each one captures a technique, a proof of concept, or a library he’s tested. When a new problem arrives, he can point Claude Code at past projects and say “combine these two approaches.” 8. The "lethal trifecta" makes AI agent security fundamentally unsolved. Whenever an AI agent has access to private data, exposure to untrusted content (like incoming emails), and the ability to send data externally (like replying to email), you have a lethal trifecta. Prompt injection—where malicious instructions in untrusted text override the agent’s intended behavior—cannot be reliably prevented. Simon has predicted a “Challenger disaster” for AI security every six months for three years. It hasn’t happened yet, but he’s pretty sure it will. 9. Start every project from a thin template, not a long instructions file. Coding agents are phenomenally good at matching existing patterns. A single test file with your preferred indentation and style is more effective than paragraphs of written instructions. Simon starts every project with a template containing one test (literally testing that 1 + 1 = 2) laid out in his preferred style. The agent picks it up and follows the convention across the entire codebase. This is cheaper and more reliable than maintaining elaborate prompt files. 10. The pelican-on-a-bicycle benchmark accidentally became a real AI benchmark. Simon created it as a joke to mock numeric benchmarks—get each LLM to generate an SVG of a pelican riding a bicycle, and compare the drawings. Unexpectedly, there’s a strong correlation between how good the drawing is and how good the model is at everything else. Nobody can explain why. It’s become a meme: Gemini 3.1’s launch video featured a pelican riding a bicycle. The AI labs are aware of it and quietly competing on it. Don't miss our full conversation: youtube.com/watch?v=wc8FBh…

@mattyp that is helpful thx

@sjorsfestt thx and good luck with everything！

@MeredithCheng22 Fully agree with keeping your product offering lean! Too many functions are confusing when targeting people. Although I must say, I really liked Karis' UI! Good luck with the pivot! I'll check it out 😎

Pfff was sick for a few days 🤢 Instantly my MRR went to 0. Time to get back in the game again

@sjorsfestt We pivot Karis to invoke now, learn a big lesson not to have plenty of features in one app. Feeling great for invoko now and will keep posting!

@MeredithCheng22 Its a must if I want to not starve 😆 How are your projects going btw I haven't seen you pop up in my feed for some time!! Are your products growing steadily? 🔥

@sjorsfestt Hhhh but that is the founder spirit!

@MeredithCheng22 Yea gonna go twice as hard upcoming days to make up for the missed work🤤

@TechByMarkandey Why cannot USA use seedance

Flova × Seedance 2.0 is here! Create cinematic AI short dramas directly on Flova using Seedance 2.0: flova.ai/?refCode=A7AV7… Why creators are switching to Flova: - High-quality visuals with smooth, natural motion - Fast, stable, and efficient generation - Quick Access: Launch Seedance 2.0 or NanoBanana in a single click, no setup required - Cost-effective: PRO users can run up to 50 concurrent generations on Seedance 2.0; other models allow 10 at a time Why Flova is the best choice for Seedance 2.0: 1. One-click access to Seedance 2.0 and NanoBanana 2. Optimized for stable, fast, and efficient AI video generation 3. All-in-one workflow: from storyboarding to cinematic-level output, no extra tools needed Flova makes producing cinematic AI content faster, simpler, and more professional. #Flovaai #Flovaseedance #Seedance2_0 #AIShorts #VideoCreation

@marclou new product？

I just listed SuperShrimp on TrustMRR ✨ trustmrr.com/startup/supers…

@natiakourdadze ☺️

@MeredithCheng22 Thanks Monica!

Which one do you prefer for the instagram carousel? 1 or 2?

@nejatian Oh no Monday is!

I am willing to accept lots of different units of measure as being acceptable, but Sunday is very clearly the first day of the week!

@harleyf that is real build in public

Success is built on the failures you don’t see. Most people only share the wins. That’s not the story. Winners don’t see failure as a life sentence. They see it as a stepping stone. That’s the difference.

@KaiXCreator Nooo I know nothing about coding but still shipping product using claudecode

Hot take: Vibe coding only works well if you already know how to code.

@EricBalchunas Me, the audience of last version 😂

Agree, annoying they don't light anything anymore in movies (esp action, fantasy). Beyond that tho, I still don't get remaking Harry Potter when the movies JUST happened. They're still available on airplanes. Millennials can just re-watch those. And I don't see Gen X or Gen Z caring about magic school sht, so who is the audience for this?