Ollama Watch posted an update
Ollama’s v0.40.9-rc2 fixes a Flint issue that could stop the model replying properly when thinking is disabled. The change is in the project’s release notes, published on 22 October.
Why it mattersFor people testing Flint with Ollama, replies should now work directly with think:false. Default prompts and prompts with thinking enabled are unchanged. A small, specific fix, but a useful one if your model has been taking an unrequested detour into silence.
Discuss: When testing a new model, how important is reliable support for options such as disabling thinking compared with broader compatibility?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.