<- Back
Comments (24)
- 361994752Sounds very interesting. Do you have plan to support gh copilot as model provider?
- YuechenLiHave you compared this to using GPT-6.1 Sol instead of GPT 6 Astra + Deepseek? From my test, 6.1 Sol is a lot more token efficient than 6 Sol while being similar to Astra in performance, and I don't really find 6 Astra to be significantly better than 6/6.1 Sol for general coding as I feel 6 Astra is only noticeably better at spatial reasoning/vision compared to 6 Sol, and 6.1 Sol really closed the gap on that front.
- thefourthchimeInteresting work, and thanks for describing how your router works internally. It's definitely a fascinating subject. How would you say this compares to Cursor's auto mode?
- svntIf you are training on data labeled by frontier models, how do you expect to exceed the performance of frontier models, other than in the cost dimension by recognizing simpler problems and routing to cheaper models?
- gitowiecCan it route to locally or LAN hosted Qwen or some other open weights model?
- ajspig1How do you handle provider variance on OpenRouter for the opensource models? Or do you use your own hosted version to mitigate this?And for both opensource and closed source, does the router account for provider quality, or catch it when a provider degrades?
- rirzeHow does this choose which models to use with any arbitrary set of model providers to work from? And why is an openrouter necessary for self-hosting?
- jamesforestwestHow do you define the model buckets, and what happens when a session genuinely needs a model that isn't in the bucket the HMM picked?
- 1minuspDoes this allow for a predefined budget?
- redroveIs the model you trained available as open weights?
- aminsamir45AGI is here!
- mrkn1[flagged]
- itsmeduncan[flagged]
- xms17189[dead]
- adurnos[dead]