283 zip codes that cover most of the US, found with Perplexity
Which zip codes, with a hundred-mile radius each, cover most of the 50 states? DeepSeek R1 on Perplexity wrote the Python, fixed it from pasted tracebacks, and drew the coverage map.
Done withPerplexitySpotted· by HN user jazzyjackson· Oct 15, 2026
Result Plus a script that maps the coverage
“I got my result of 283 zip codes that cover most of the 50 states with a hundred mile radius from each zip, plus a script to draw a map of the result”
Spotted: found in the wild. Details are as reported by the source above and have not been independently verified.
What they did
Used DeepSeek R1 through Perplexity Pro to write Python that finds a set of zip codes whose hundred-mile radii cover most of the country, pasting tracebacks back in whenever numpy and pandas misbehaved so it could rewrite the code.
How it went
They came away very impressed: the result was 283 zip codes covering most of the 50 states, plus a script to draw a map of the coverage.
Try it yourself with Perplexity
Write a Python script that finds the smallest set of [US zip codes or locations] such that circles of [radius] miles around them cover [the whole country or a list of addresses]. Use a free zip code dataset, explain the method in plain terms, and draw a map of the result. If you hit an error, show me the fix.
A starting prompt written by Agents in the Wild. Fill in the [brackets], and check what the agent does before it sends, pays for or deletes anything.
Bessemer Venture Partners' investment and legal teams lived in manual research. Perplexity Enterprise now handles it and tracks news on 400+ portfolio companies, per Perplexity.
About 15k pages of discovery stood between a solo practice and a summary judgment motion. Claude ran OCR, built embeddings and search scripts, then found evidence for each assertion, with traces to check.
Tracking which newsletters break into Substack's top 200 meant clicking and copy-pasting. Claude in Chrome now scrapes the charts every Tuesday, and Cowork turns the data into a spreadsheet report.
When a new OpenClaw beta added Telegram message streaming, they asked their agent what else had changed. It read 15+ merged pull requests, compared them to the current version, and gave an upgrade recommendation.
Before a conference with 40 people they had never met, LinkedIn research normally takes an evening. Claude Code researched the attendees in parallel via LinkedIn and Chrome MCP, producing a full briefing in 5 minutes.
A master's thesis in a fast-moving field and too many new papers. A weekly Codex automation searches arXiv, triages only new papers and files promising ones into Zotero, with fewer hallucinated citations.