Hacker News new | ask | show | jobs
by gadflyinyoureye 59 days ago
I've been assuming this for a while. If I have a complex feature, I use Opus 4.6 in copilot to plan (3 units of my monthly limit). Then have Grok or Gemini (.25-.33) of my monthly units to implement and verify the work. 80% of the time it works every time. Leave me plenty of usage over the month.
2 comments
sgc 59 days ago
I have a very newcomer-type question. What is the output format of your plan such that you can break context and get the other LLM to produce satisfactory results? What level of details is in the plan, bullet points, pseudo-code, or somewhere in the middle?
link
andai 59 days ago
Yeah I've been arriving at the same thing. The other models give me way more usage but they don't seem to have enough common sense to be worth using as the main driver.

If I can have Claude write up the plan, and the other models actually execute it, I'd get the best of both worlds.

(Amusingly, I think Codex tolerates being invoked by Claude (de facto tolerated ToS violation), but not the other way around.)

link
zozbot234 59 days ago
I don't think there's any ToS violation involved? AIUI you can use GPT models with any harness, at least at present.

You could nonetheless have Codex write up the plan to an .md file for Claude (perhaps Sonnet or even Haiku?) to execute.

link
andai 59 days ago
I meant with the subscriptions, which are heavily subsidized. API billing is free game.

Anthropic's been against 3rd party usage of the subs, including, I believe, 3rd party software invoking Claude Code.

OpenAI, from what I heard, is the only company tolerating this type of usage (for now).

So my point was, if you get a subscription from both, you could let Claude "drive" Codex, but not the reverse.

And while it sounds silly, it might actually be the only way to get real work done at the moment, with usage being exhausted so quickly.

link