I think the jury is still out on K3/Q3.8 and if they are equivalent to Opus or Fable.
I think the jury is still out on K3/Q3.8 and if they are equivalent to Opus or Fable. Benchmarks have gotten incredibly murky and I've tried models that are "the same as X model" and been unimpressed. I've tried other models with Claude Code and with tools like OpenCode or Pi and nothing has really come close to Claude Code using Anthropic's models (mostly Opus 4.8). I'm not saying these other models are trash, just that I'm not quite ready to put them on equal footing to Anthropic or OpenAI models. I think the future of LLM coding (and more) is probably routers that decide on a per-task basis which model to route to. Know when to use Fable/Opus and when to fall back to DeepSeek/Kimi/Qwen, even all the way to local models. Of course that's not in the frontier lab's interest but it feels like there is a lot of low-hanging fruit there. I hate that right now it's pretty much "just use the same model for planning/execution/etc" (without standing on your head).
Posted by joshstrange on Jul 20, 2026, 4:01 PM
Tags
Related issues
- Near impossible to do it robustly without AI, since a mesh is a blob of triangles and vertices, it doesn't really know if something is a ...
- Because I learned on this, it made learning everything else that much harder.
- For the old school (I hate that that’s arguably applicable) AI dating types, and so on.
- > I hate that you are reducing my craft to just the end results and nothing else.
- > This of course is the cornerstone of Western culture and no well-educated person can be without a knowledge of what is in it.
- I hate that it's hidden too.
Raise real-world problems, find people facing the same issue, and discuss solutions.2,000 issues0 comments
complaint (EdTech)
Near impossible to do it robustly without AI, since a mesh is a blob of triangles and vertices, it doesn't really know if something is a ...
Because I learned on this, it made learning everything else that much harder.
For the old school (I hate that that’s arguably applicable) AI dating types, and so on.
> I hate that you are reducing my craft to just the end results and nothing else.
> This of course is the cornerstone of Western culture and no well-educated person can be without a knowledge of what is in it.
I hate that it's hidden too.
I think the jury is still out on K3/Q3.8 and if they are equivalent to Opus or Fable.
I didn't find a direct proof earlier, just assertions - I've only seen it proved in textbooks that aren't linkable.
I think the jury is still out on K3/Q3.8 and if they are equivalent to Opus or Fable.
I think the jury is still out on K3/Q3.8 and if they are equivalent to Opus or Fable. Benchmarks have gotten incredibly murky and I've tried models that are "the same as X model" and been unimpressed. I've tried other models with Claude Code and with tools like OpenCode or Pi and nothing has really come close to Claude Code using Anthropic's models (mostly Opus 4.8). I'm not saying these other models are trash, just that I'm not quite ready to put them on equal footing to Anthropic or OpenAI models. I think the future of LLM coding (and more) is probably routers that decide on a per-task basis which model to route to. Know when to use Fable/Opus and when to fall back to DeepSeek/Kimi/Qwen, even all the way to local models. Of course that's not in the frontier lab's interest but it feels like there is a lot of low-hanging fruit there. I hate that right now it's pretty much "just use the same model for planning/execution/etc" (without standing on your head).
Comments (0)
No comments yet. Start the discussion.