Andrej Karpathy just explained the future of software engineering without directly saying it.
The best AI engineers are no longer “prompting.”
They’re building systems around the agents.
Karpathy’s biggest insight wasn’t:
“Claude can code.”
It was:
LLMs become dramatically better when you force them into disciplined workflows.
That’s why "CLAUDE.md" files are suddenly everywhere.
Not because they’re prompts.
Because they behave like an operating system for the agent.
Karpathy called out the exact problems with AI coding:
- models assume instead of asking
- they overengineer simple tasks
- they hide confusion
- they rewrite unrelated code
- they optimize for completion, not correctness
So developers started encoding rules directly into the workflow:
→ Think before coding
→ Simplicity first
→ Surgical edits only
→ Goal-driven execution
And the results are wild.
People are now running multiple Claude Code agents in parallel like engineering teams:
• one agent researching
• one debugging
• one writing tests
• one optimizing code
• one validating outputs
Not “AI assistance.”
Actual orchestration.
And this part from Karpathy changes everything:
“Don’t tell the model what to do. Give it success criteria and let it loop.”
That is the shift.
From:
“write this function”
To:
“here’s the goal, constraints, tests, and verification system — now iterate until correct.”
The craziest part?
This already feels like a phase shift in engineering.
A lot of developers quietly went from:
80% manual coding → to 80% agent-driven coding in just months.
Not because AI became perfect.
Because the leverage became impossible to ignore.
We’re entering an era where the highest leverage engineers won’t necessarily be the best coders.
They’ll be the people who build the best systems around AI agents.
Excited to share how Anthropic's data team has automated 95% of business analytics queries with Claude. Blog post covers how we approach evals, ablations, and online validation!
Very excited: A few days ago, our first R package {#newsanchor} reached 1000+ downloads on #CRAN. It helps to access @NewsAPIorg. Read more about it on our blog.
Or simply type:
install.packages(“newsanchor“).
#rstats https://t.co/SimQ9T2shB
We rebuilt the Stocktwits symbol page from the ground up!
Cleaner social-first feed, a new Top Voices module to surface the sharpest minds on any ticker, and a Related Symbols section to discover connected plays. We’re putting the community front and center.
I believe he is a great physicist, probably even knows how the current AI technology could help physics better than anyone. But that does not make him an expert about the current AI technology, claiming its limit or the lack thereof.