PunchPHOTOS: Osimhen resumes training ahead of Kasimpasa clashBollywood HungamaKiara Advani and Sidharth Malhotra announce second pregnancy with adorable post: “Blessed once again”The Jerusalem PostExtremist Israeli settlers attack Palestinian home in West Bank, set vehicle on fire - reportESPN DeportesMerino rescató a España y le dio la agónica victoria ante Croacia en la Nations LeagueDaily MaverickDRAFT DODGING: Three years, 6,000 pages, no labels: Who’s stalling SA’s food warnings?ESPNMessi marks tearful Argentina farewell with goal: Wish I could play foreverInquirerProsecution seeks to show Dutertes hid P96M via unused manager’s checksThe South AfricanLionel Messi retires from international football in styleSky TG24Lewis Capaldi compie 30 anni, le sue canzoni più famose da Someone you Loved a Forget MeBusiness AMAI-aandelen stuwen S&P 500 en Nasdaq naar nieuwe recordhoogtesZDF heuteEntdecken Sie das ZDF-NachrichtenstudioRTP DesportoPortugal perde com Itália no Mundial feminino de hóquei
The Daily Newsstand · Free, Always
Wednesday, October 7, 2026

Claude Code creator Boris Cherny on what not to miss while prompting Claude

Translate

Claude Code creator Boris Cherny shares what not to miss while giving prompt to Claude; says: There's no secret to ...

Anthropic’s Claude Code creator, Boris Cherny has offered a simple piece of advice to users who are trying to get better results from AI models. In a post shared on social media platform X (formerly known as Twitter) Cherny asked the users to talk to Claude the same way they would talk to a coworker.

As per Cherny users no longer need highly structured and very detailed prompts for most tasks, as modern AI models are increasingly capable of figuring out how to achieve a goal on their own. In the post shared on X, Cherny revealed that he was surprised that people were surprised by the way he prompts Claude. “Talk to Claude the way you would a coworker. There's no secret to prompting. There's no need to be overly scaffolded or prescriptive for most tasks.

Give Claude a goal, and it will figure it out,” he wrote.

Anthropic’s Boris Cherny reveals what matters on prompting AI today

Cherny contrasted the current approach with the early days of Claude's Sonnet 3.5 models, when the exact wording of a prompt mattered a great deal. Today's models, he suggested, need less hand-holding on the "how" and more clarity about the "what."He said it is now much more important to communicate three things to the model:1. What you want it to do2. How much effort you want it to spend3. How it should verify that it did the right thingThe comments align with advice Cherny has shared in public discussions, where he has argued that many users make the mistake of over-specifying every step instead of clearly defining the desired outcome.

Modern AI models are often better used by describing the goal and success criteria rather than dictating a rigid sequence of actions.

The prompt that caught attention

Alongside his comments, Cherny shared an example of a prompt he uses with Claude.In the example, he asked the AI to create an interactive artefact about a recent podcast episode on Home Depot's acquisition strategy. Rather than providing detailed step-by-step instructions, he described the end goal: a visually rich, interactive experience that highlights key business lessons.The prompt asked Claude to make the output “beautiful and interactive,” focus on business wisdom from the episode, use extensive reasoning and iteration, and incorporate elements such as watercolour illustrations, historical photographs and visual storytelling inspired by publications such as The New Yorker and The New York Times.Notably, the prompt emphasised the desired outcome and quality bar rather than prescribing a detailed process, reflecting the prompting philosophy Cherny advocates.

View the original on Times of India →

KioskNews shows a cleaned-up reading view extracted from the publisher’s page — the original always lives on their site, not ours.