Composer: Building a fast frontier model with RL
1–10 of 169 posts
Re: Composer: Building a fast frontier model with RL
#2Very cool, congrats!
Re: Composer: Building a fast frontier model with RL
#3Where is the comparison with Sonnet 4.5? That would be the only thing that matters, really.
Re: Composer: Building a fast frontier model with RL
#4Where is the comparison with Sonnet 4.5? That would be the only thing that matters, really.
> "Best Frontier" includes GPT-5 and Sonnet 4.5, which both outperform Composer.
Re: Composer: Building a fast frontier model with RL
#5I wonder if this custom model is trained on cursor users. There’s a lot of potential on how much better a custom model could be the closer it is integrated with the product. Having the model learn to adapt to different user preferences would make it stand out compared to memoryless frontier models.
Re: Composer: Building a fast frontier model with RL
#6I love Cursor. I've tried Copilot/Claude/etc. but keep coming back to Cursor. I just want to work, and Cursor tab complete is dang accurate, esp. for refactoring tasks.
Re: Composer: Building a fast frontier model with RL
#7Where is the comparison with Sonnet 4.5? That would be the only thing that matters, really.
> "Best Frontier" includes GPT-5 and Sonnet 4.5, which both outperform Composer.
>> "Best Frontier" includes GPT-5 and Sonnet 4.5, which both outperform Composer.
Looking at the graph, it would appear there's an implicit "today" in that statement, as they do appear poised to equal or surpass Sonnet 4.5 on that same benchmark in the near future.
Re: Composer: Building a fast frontier model with RL
#8While I am excited to see a new model, I am skeptical when there is so much vagueness - charts with "frontier models" without actually spelling out which ones, charts with no numbers (time axis, or in one chart - entirely).
Re: Composer: Building a fast frontier model with RL
#9I wonder if this custom model is trained on cursor users. There’s a lot of potential on how much better a custom model could be the closer it is integrated with the product. Having the model learn to adapt to different user preferences would make it stand out compared to memoryless frontier models.
The fact that you are wondering this is bad. You definitely should know this. _ALL_ the online ai providers are training on your data. They have more expensive enterprise plans if want to opt out.
Re: Composer: Building a fast frontier model with RL
#10People on here love to be contrarian about Cursor, but I’ve tried all the popular alternatives (Copilot, Claude Code, Codex, Gemini CLI, Cline) and found Cursor’s overall experience to just be unmatched. A big part of that is its speed, another its reliability.
It’s the only coding agent I’m actually really motivated to use out of the box because it really does make me feel more productive while the others keep messing up the project, from way too large changes I didn’t ask for all the way to constant syntax and request errors.
It’s the only coding agent I’ve used that feels serious about being a product rather than a prototype. Their effort in improving their stack is totally paying off.