News: 0180530199

  ARM Give a man a fire and he's warm for a day, but set fire to him and he's warm for the rest of his life (Terry Pratchett, Jingo)

Creator of Claude Code Reveals His Workflow

(Tuesday January 06, 2026 @10:30PM (BeauHD) from the take-notes dept.)


Boris Cherny, the creator of Claude Code at Anthropic, revealed a deceptively simple workflow that [1]uses parallel AI agents, verification loops, and shared memory to let one developer operate with the output of an entire engineering team. "I run 5 Claudes in parallel in my terminal," Cherny wrote. "I number my tabs 1-5, and use system notifications to know when a Claude needs input." He also runs "5-10 Claudes on claude.ai" in his browser, using a "teleport" command to hand off work between the web and his local machine. This validates the " [2]do more with less " strategy Anthropic's President Daniela Amodei recently pitched during an interview with CNBC. VentureBeat reports:

> For the past week, the engineering community has been dissecting a [3]thread on X from Boris Cherny, the creator and head of Claude Code at Anthropic. What began as a casual sharing of his personal terminal setup has spiraled into a viral manifesto on the future of software development, with industry insiders calling it a watershed moment for the startup.

>

> "If you're not reading the Claude Code best practices straight from its creator, you're behind as a programmer," wrote Jeff Tang, a prominent voice in the developer community. Kyle McNease, another industry observer, went further, declaring that with Cherny's "game-changing updates," Anthropic is "on fire," potentially facing "their ChatGPT moment."

>

> The excitement stems from a paradox: Cherny's workflow is surprisingly simple, yet it allows a single human to operate with the output capacity of a small engineering department. As one user noted on X after implementing Cherny's setup, the experience "feels more like Starcraft" than traditional coding -- a shift from typing syntax to commanding autonomous units.



[1] https://venturebeat.com/technology/the-creator-of-claude-code-just-revealed-his-workflow-and-developers-are

[2] https://www.cnbc.com/2026/01/03/anthropic-daniela-amodei-do-more-with-less-bet.html

[3] https://x.com/bcherny/status/2007179832300581177


with less? (Score:1)

by Anonymous Coward

1 Boris, 5 Claudes in terminal, 10 Claudes in Cloud

I wouldn't call the datacenter required to run those Claudes in the Cloud 'less' than say 16 laptops that 16 devs would use.

Re: (Score:2)

by Mr. Dollar Ton ( 5495648 )

Well, it is AI slop from venture beat, what did you expect?

TFA sounds like Co-pilot orchaestration (Score:2)

by echo123 ( 1266692 )

TFA sounds like simple [1]orchestration compared to Co-pilot [github.blog]. At least co-pilot allows [2]your 'team' [visualstudio.com] to have [3]various skills [microsoft.com] as they work cooperatively with each other. In other words, the technology is similar yet co-pilot has a whole API developed.

[1] https://github.blog/ai-and-ml/github-copilot/how-to-orchestrate-agents-using-mission-control/

[2] https://code.visualstudio.com/docs/copilot/agents/overview

[3] https://www.microsoft.com/en-us/microsoft-copilot/copilot-101/ai-agents-types-and-uses

Re: (Score:2)

by echo123 ( 1266692 )

...a developer agent might use Anthropic Claude, a documentation agent might use Gemini, and a testing agent use Codex, because those LLMs have their specialties that set them apart. Co-pilot manages the team.

In the Pipe, Five by Five (Score:2)

by dohzer ( 867770 )

> "feels more like Starcraft" than traditional coding

YOU MUST CONSTRUCT ADDITIONAL POINTERS

The only problem, though, is getting to that point (Score:3)

by ebunga ( 95613 )

See... for that to actually work for you... you already need to be an expert... otherwise you're going to vibecode yourself into a national security incident.

Baloney (Score:2)

by backslashdot ( 95548 )

I've tried it with 2 and it chokes.

dear god (Score:1)

by SumDog ( 466607 )

That code as got to be horrific. Even the latest Opus model just adds a ton of Exception catching for general error management, in every language from Python to C#. It's absolutely shit and I can tell when other devs didn't even bother to fix that crab and use generated bullshit in code reviews.

Talent does what it can.
Genius does what it must.
You do what you get paid to do.