@FinanceYF5: Anthropic's Boris Cherny points out that programming is moving towards a higher level of abstraction. A year ago, developers' workflow was to first write code in an IDE, then prompt multiple Claude instances in parallel. Now, the workflow has evolved to writing loops to call Claude, and letting it make autonomous decisions...
Summary
Anthropic's Boris Cherny points out that programming is moving towards a higher level of abstraction, with workflows shifting from manually writing code to letting Claude make autonomous decisions, and predicts that the next paradigm shift will arrive this year.
View Cached Full Text
Cached at: 06/08/26, 09:23 AM
Anthropic’s Boris Cherny points out that programming is moving toward higher levels of abstraction.
A year ago, a developer’s workflow was to write code in an IDE and then prompt multiple Claude instances in parallel. Now, the workflow has evolved into writing loops that call Claude, allowing it to autonomously decide on the next steps.
“The next paradigm shift will come this year.” https://t.co/rvobEGIEFk
Similar Articles
@seclink: Last week, Peter Steinberger wrote about the workflow Boris Cherny adopted at Anthropic: using Claude Code to run looped tasks, such as monitoring Pull Requests (PRs) or scanning GitHub, among others...
Boris Cherny at Anthropic uses Claude Code to run looped tasks, automating workflows like PR monitoring and GitHub scanning, allowing him to orchestrate dozens of tasks from just his phone. Anthropic reports that over 80% of its production code is now written by Claude, showcasing the potential of agentic coding.
@Mikocrypto11: Boris, the creator of Claude Code, shared a crucial shift: "I no longer write prompts for Claude. I write loops and let the loops do the work. My job is to write loops." This is actually where many people get stuck with Claude Code...
Boris, the creator of Claude Code, shares a crucial shift: moving from writing prompts to writing loops, letting the model iteratively progress tasks in a repeatable loop instead of providing a one-time answer.
@FinanceYF5: Anthropic is hiring 1000 freelance software engineers to train Claude Code. Each task pays $280. They write prompts, compare code outputs, test the model's follow-up responses, and teach Claude how real developers work. It's like handing...
Anthropic is hiring 1000 freelance software engineers to train Claude Code, with each task paying $280. The engineers will write prompts, compare code outputs, test model responses, and teach Claude how real developers work.
@4rblaber: head of anthropic: "people get stuck trying to write the perfect line of code. stop doing that" "just tell claude what …
Anthropic CEO Dario Amodei advises developers to stop manually coding and instead guide AI models like Claude with goal-driven prompts, while OpenAI co-founder Andrej Karpathy echoes similar 'vibe coding' sentiments in a podcast, signaling a shift to AI-driven development workflows.
@shitunote: Former Google CEO Eric Schmidt described a dramatic shift in programming paradigms in a recent video interview: "Programmers no longer write code line by line. Instead, they wake up in the morning, go to the office (because people have social needs); then gather 10 Claude friends or 10 Gemini friends (i.e., AI agents), set them up with target functions, and watch them generate code; then go out for lunch, ensuring the AI keeps working; come back in the afternoon, assign a long enough task for the AI to run overnight, and go home to spend time with family. The next morning, the results are there."
Former Google CEO Eric Schmidt described a future programming paradigm in an interview: programmers will command multiple AI agents (like Claude, Gemini) to generate code instead of manually coding. This tweet sparked discussion, asking if the description is accurate.