Important disclaimer for anyone using Cursor: make sure to disable "data sharing" in your account settings, as it is enabled by default and old accounts are automatically opted into it.
Improving Composer through real-time RL
21–30 of 45 posts
Re: Improving Composer through real-time RL
#22Important disclaimer for anyone using Cursor: make sure to disable "data sharing" in your account settings, as it is enabled by default and old accounts are automatically opted into it.
Do you have evidence for those claims? I don’t mean to be contrary or subversive, I’d just be interested in seeing how this is actually taking place.
Re: Improving Composer through real-time RL
#23the rl loop here is clever but i wonder how the reward signal degrades over time. if you're optimizing for user acceptance of suggestions, you're inevitably training on a mix of "this was actually correct" and "i accepted because editing the suggestion was more work than accepting it." that second case creates a subtle bias toward suggestions that are close-enough-to-not-bother-fixing rather than actually correct.
also curious whether they see different convergence patterns across languages. my gut says something like python where theres more stylistic variation would be harder to get a clean reward signal vs something like rust where there are fewer idiomatic ways to do things.
Re: Improving Composer through real-time RL
#24Step 1: take an open source model with zero acknowledgement. Step 2: build on someone else's infrastructure innovations with zero acknowledgement. Step 3: Write a blog post with "unprecedented" and "100x" and "trillions" in the first paragraph. Seriously, this seems like cool work and enjoyed the post. But my basic trust in them has completely tanked.
I’m not familiar with 2 of these 3 stories so I’m mostly just impressed by the RL turnaround (4 hours!?) and sharing knowledge on the fly off using fine tuned models at scale.
For the gossipy part, I love Kimi, but find it hard to get worked up about them not labelling their model Kimi when Kimi was the base. Especially because Kimi…has had…some issues…being able to distinguish itself from Claude…
Re: Improving Composer through real-time RL
#25Important disclaimer for anyone using Cursor: make sure to disable "data sharing" in your account settings, as it is enabled by default and old accounts are automatically opted into it.
Do you have evidence for those claims? I don’t mean to be contrary or subversive, I’d just be interested in seeing how this is actually taking place.
To be very precise about session recording: you can inspect the Cursor binary and see that it comes bundled with rrweb and full telemetry infrastructure setup is in place: mouse movements, clicks, scroll positions, etc. on top of the codebase and prompts being sent over the wire.
However, I have edited my other claims for now and you can consider them provisionally retracted. My original advice about turning off data sharing stands. You are right to ask for more evidence given the severity of the claims. I think this merits a deeper dive, and a throwaway hacker news comment might not be the best channel for it. Stay tuned ;)
Re: Improving Composer through real-time RL
#26[flagged]
Re: Improving Composer through real-time RL
#27[dead]
Re: Improving Composer through real-time RL
#28What are with these comments? Did no one even read the article. Not once is composer 2, or kimi, or anything mentioned... because the article is about Composer 1.5.
I mean sure the techniques are probably the same in 2 but its not like they're exactly advertising composer 2 here lol
Re: Improving Composer through real-time RL
#29If the model "improves" every 5 hours, how do you have any guarantee of model consistency across long coding sessions?
Yeah, this feels tricky
If the model changes every few hours, we’re basically debugging against a moving target - and that gets expensive fast.
Re: Improving Composer through real-time RL
#30Step 1: take an open source model with zero acknowledgement. Step 2: build on someone else's infrastructure innovations with zero acknowledgement. Step 3: Write a blog post with "unprecedented" and "100x" and "trillions" in the first paragraph. Seriously, this seems like cool work and enjoyed the post. But my basic trust in them has completely tanked.
I don't though it works and these guys are raking in the money.
The wider audience of devs or people paying up for Cursor don't care about the morals old school OSS devs hold.