this post was submitted on 08 Jul 2026
576 points (99.5% liked)
Technology
86159 readers
3349 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
- Check for duplicates before posting, duplicates may be removed
- Accounts 7 days and younger will have their posts automatically removed.
Approved Bots
founded 3 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Neither Claude code neither codex is actually vendor specific, they just don't tell you that you can config other providers, including local
However opencode is pretty nice too, so if you like it, use that. I personally find that opencode with GLM 5.2 or Kimi K2.7 isn't actually that great, it'll hallucinate more than Claude code or Codex with their respective first party models. I think it's the models themselves rather than opencode itself though, as when I use GPT for planning and hand it off to deepseek flash to do the actual work, it's more or less fine.
I suspect behind the scenes, the first parties are sending your requests to multiple targets and sending you back quorum.
Not impossible, but also the thinking process reduces the need for something like that. Anything in the context gets regurgitated back and forth multiple times so the model has multiple opportunities to flag something as being weird.
Incidentally if you actually want to do something like that yourself, I believe OpenRouter has a feature for that. But of course it means you can essentially add up each model's costs and that's your new cost per prompt (not exact since output token count will differ, but on average).