← Back to context

Comment by ojr

2 days ago

I use Gemini 3 Flash, I've seen the Claude Code setups, bullish on Anthropic people are driving up tokens but I am able to produce outcomes with a fraction of the money.

10 comments

ojr

Reply
hmokiguess  2 days ago

Do you mind sharing your workflow? What do you mean by fraction of the money, in my case personally, I'm yet to reach a session limit on the subscription plan. I'm not "tokenmaxxing" as they say, so hard to see a scenario in which the plan is expensive for the value I get.

  • dist-epoch  2 days ago

    If you don't hit a limit running Opus, it means you are very much in the loop.

    For example you probably don't have days where you ask Opus to review your whole code base and look for code duplication/technical debt/robustness issues, and then to fix some of the found issues, and do this 3-5 times until no big issues are found anymore.

    • hmokiguess  2 days ago

      What’s your prompt for this, the way you described it made it seem like there’s a generalizable way I can go about this. I just rely on a testing pipeline instead so can’t think of why I would need to proactively find holes where tests haven’t already done that for me.

      4 replies →

  • ojr  2 days ago

    I spend around $20 a month through API fees using my own harness, https://slidebits.com/isogen. Nothing too special, I prompt it produces file changes using grep and vector search and I can individually accept which files.

    I also work on a consumer AI application https://apps.apple.com/us/app/slidebits-studio/id1138731130

    For comparison someone showed me an internal company tool he was working on. He had Claude agents dangerously skipping permissions and firing up github branches through a vm sandbox just to make a single feature change. One agent to code and the other to review.