LinkedIn Content Strategy & Writing Style
Building AI and building with AI
0 people tracking this creator on Viral Brain
John Crickett positions himself as a seasoned engineering veteran who bridges the gap between principled software craftsmanship and the frontier of AI automation. His content strategy centers on debunking the "hype cycle" by applying 30 years of architectural rigor to modern AI agents, focusing on themes like context engineering, modularity, and the human responsibility of code ownership. He is notable for his pragmatic skepticism, often challenging the industry's obsession with raw output by arguing that 1,800 AI commits are useless without human-led clarity and maintainable foundations. This creates a unique intersection where legacy engineering wisdom meets cutting-edge AI workflows, transforming the conversation from how to generate code to how to architect systems that remain robust in an AI-first world.
205.1K
27.1K
433
—
14.0
27
2
Software engineers: Context switching kills productivity. Also software engineers: I'm now managing 19 AI agents and doing 1800 commits a day. We’ve spent years complaining that managers who expect…
Did you know you can build a GPT in just 200 lines of pure Python? Yesterday Andrej Karpathy did just that, sharing microgpt. Training and inference, all in one file. Study the code and you'll see ho…
I've loved AI for a long time. Not the hype cycle version. The real thing. Which is exactly why I can see its flaws. Something strange is happening in tech discourse. If you're not a full believer,…
"AI can't handle a multi-million line codebase." I keep hearing this. But I want to challenge something more fundamental. Is there really such a thing as a multi-million line codebase? Every large…
"You didn't write the code, so you don't truly understand it." Is a common argument against AI coding tools. But it doesn't hold up. I just read another post making this case. It sounds reasonable o…
I've been documenting my views on AI-assisted coding. I believe in strong opinions, weakly held, so I'd love your thoughts, feedback, and challenges on what follows. When we argue about whether LLMs…
14.0 posts/week
Posts / Week
0.6 days
Days Between Posts
2
Total Posts Analyzed
HIGH
Posting Frequency
432.6666666666667%
Avg Engagement Rate
STABLE
Performance Trend
230
Avg Length (Words)
HIGH
Depth Level
ADVANCED
Expertise Level
0.86/10
Uniqueness Score
YES
Question Usage
0.2%
Response Rate
Writing style breakdown
<start of post>
AI is going to replace junior developers." This is the headline I see every single day.
But it misses the point of what a junior developer actually is.
A junior isn't just a "code producer." They are the future seniors of your organisation. If you stop hiring them because an LLM can write a boilerplate React component, you aren't being efficient. You're eating your seed corn.
Think about the long-term implications for a moment.
In five years, where will your senior engineers come from? You can't hire "seniors" if no one was ever a "junior."
The work changes, but the need for growth doesn't. We need to shift our focus from "how much code can they write" to "how quickly can they learn to navigate complex systems." AI is a tool that helps them get there faster, not a reason to close the door.
The bottom line: Don't use AI as an excuse to stop investing in people. Use it as a way to accelerate their journey from junior to expert.
To the hiring managers out there: Has AI changed your headcount plans for the year? Or are you doubling down on mentorship?
<end of post>
Sign in to unlock the full writing analysis
Nail your LinkedIn strategy with ViralBrain.
Analyze and write in John Crickett's style. Grow your LinkedIn to the next level.