@AQuetto@yul_magdaleno If this genuinely happened, please DM me your ticket number and i’ll look into it. We shouldn’t be deleting your settings, especially when it comes to billing!
@RoundtableSpace you should use multitask mode - it’s built for multi-agent orchestration and allows you to steer and monitor each task with the help of a “owner” agent
https://t.co/DkpIombAs7
@jasperdevs benchmarks are a sub-par measurement of model performance unfortunately
even if not on purpose, it’s easy to put a huge value on benchmark performance when building a model, to the point where the model may be over-fitted to the benchmarks but worse in day to day use
there was pizza at the last one, so odds are there’s pizza again too. also some impressive judges there for the evening!
sign up below.
and tell your friends to sign up too.
even if you just go for the pizza 🍕
https://t.co/4wPbhYCua9
my good friend @frankterpo is hosting his second Cursor hackathon, in an amazing space in waterloo
theres a 50% chance i’ll be there, but even if im not, there’s free cursor credits on offer just for attending, and even more if you code something cool!
(unaffiliated thoughts)
@umbrel should have a cloud offering.
i’m not tin-foil hat enough to self-host on a box that lives in my house, and while i’m perfectly capable, i have no desire to configure and manage a VPS
the team did an internal test of this model last week
the whole company (bar a few exceptions) had all their cursor chats redirected to composer 2.5 for like 2 days.
i didn't even notice, which I think is testament to the progress of this model. go use it, its very good.
Introducing Composer 2.5, our most powerful model yet.
It's more intelligent, better at sustained work on long-running tasks, and more reliable at following complex instructions.
For the next week, we’re doubling the included usage of the model.