TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Show HN: I used GPT-4-Vision to mimic myself in emails and Intercom

1 pointsby vignesh_wararabout 1 year ago
Hello everyone,<p>Hey, I am Vignesh. When I launched my previous product, Keep it Shot, it got some attention on Twitter to the point where I was spending two straight days on repetitive customer support, answering emails and Twitter DMs. I passionately hated it. Don&#x27;t get me wrong, I love talking to my customers, but I just can&#x27;t answer simple, repetitive responses. That&#x27;s when I came up with the idea for Brain Mimic.<p>Brain Mimic is a browser extension that saves what you type on the browser and mimics you on email, Slack, or any site input with one click, without the need for any additional prompts.<p>One thing I noticed when building Brain Mimic is that people are talking a lot of good stuff on Twitter about how Claude is outperforming GPT-4. I agree it does, but only for text. When I provided complex screenshots to both Claude and GPT-4 with vision, GPT-4V always understands what questions it should respond to, although there are still some caveats. But it has been working and has saved a ton of time in mimicking me for writing in the past week.<p>Please let me know if you have any feedback.<p>Vignesh

no comments

no comments