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.

Ask HN: Claude 3.7 or Gemini 2.5 Pro?

8 pointsby apt-apt-apt-apt3 days ago
I have been using Cursor with Gemini 2.5 Pro (exp-03-25) for TypeScript, and haven't felt the need to switch nor can I tell any difference between the two. Claude or Gemini?

6 comments

muzani3 days ago
Claude 3.7 is a little overeager. It&#x27;ll solve problems you don&#x27;t tell it to solve. Like I give it a screenshot of an app and ask it to do a button; it&#x27;ll do the status bar as well. It&#x27;s somewhat like a jerk genie and I feel like I&#x27;m writing a contract rather than working with an assistant. Claude 3.5 doesn&#x27;t have this problem.<p>Gemini 2.5 Pro will one shot complex instructions and even read between the lines. The drawback is that it can often overthink as well. One example was I want to deselect a dropdown if I recreate it (e.g. select state when changing countries). The ideal solution is to just check this on the view layer. Gemini 2.5 pro is terrible at this - it&#x27;ll go down into lower layers and overengineer, when the solution should just to set as null if the new dropdown doesn&#x27;t contain the same text.<p>GPT 4.1 has been quite good lately, but it&#x27;s not quite as agentic and it will ask you a lot of questions and request confirmation to begin. It is perfect for workflows where you aren&#x27;t certain yourself.<p>GPT is also smartest from the visual angle, able to read color variations well and designs them well. Claude is the worst visually.
ramesh313 days ago
Claude is still king for coding. Anything else I&#x27;m reaching for Gemini these days. The 1M context and the speed makes it way better for writing docs and explaining code.
bicepjai3 days ago
Today I tried Gemini and have better experience with it on cline. So much rate limiting on Claude probably everybody using them. Also Gemini is expensive. I have already burned 200 dollars for one weekend incomplete project
christophilus3 days ago
I’ve found Cursor to be hit or miss, but mostly miss in a big TS codebase. That is regardless of the underlying AI model. Claude Code, though, has been excellent so far. It seems the agent matters more than I’d realized.
评论 #43968077 未加载
评论 #43968057 未加载
paulcole3 days ago
Pretty much doesn’t matter in my experience.<p>If it’s a model you’ve heard of, it’s pretty good and pretty much the same as the other ones you’ve heard of.
hnlurker222 days ago
ChatGPT all the way.